Download:
pdf |
pdf2012 National Survey of
Bicyclist and Pedestrian
Attitudes and Behavior
Volume 3: Methodology Report
DISCLAIMER
This publication is distributed by the U.S. Department of Transportation, National Highway
Traffic Safety Administration, in the interest of information exchange. The opinions, findings,
and conclusions expressed in this publication are those of the authors and not necessarily those
of the Department of Transportation or the National Highway Traffic Safety Administration. The
United States Government assumes no liability for its contents or use thereof. If trade names,
manufacturers’ names, or specific products are mentioned, it is because they are considered essential
to the object of the publication and should not be construed as an endorsement. The United States
Government does not endorse products or manufacturers.
Suggested APA Format Citation:
Schroeder, P. & Wilbur, M. (2013, October). 2012 National survey of bicyclist and pedestrian
attitudes and behavior, volume 3: Methodology report. (Report No. DOT HS 811 841 C).
Washington, DC: National Highway Traffic Safety Administration.
1. Report No.
DOT HS 811 841 C
2. Government
Accession No.
3. Recipient’s Catalog No.
4. Title and Subtitle
5. Report Date
2012 National Survey of Bicyclist and Pedestrian
Attitudes and Behavior
Volume 3: Methodology Report
October 2013
7. Author(s)
8. Performing Organization Report No.
Paul Schroeder, Melanie Wilbur
Abt SRBI, Inc
9. Performing Organization Name and Address
10. Work Unit No. (TRAIS)
Abt SRBI, Inc
8405 Colesville, Road, Ste 300
Silver Spring, MD 20910
6. Performing Organization Code
11. Contract or Grant No.
DTNH22-11-C-00219
13. Type of Report and Period Covered
12. Sponsoring Agency Name and Address
Survey conducted July 12, 2012 to
November 18, 2012
Office of Behavioral Safety Research
National Highway Traffic Safety Administration
1200 New Jersey Avenue SE.
Washington, DC 20590
14. Sponsoring Agency Code
15. Supplementary Notes
16. Abstract
The 2012 National Survey of Bicyclist and Pedestrian Attitudes and Behavior is the second
survey on this topic conducted for the National Highway Traffic Safety Administration
(NHTSA). Data collection was conducted by Abt SRBI, Inc, a national research
organization. The survey utilized an overlapping dual frame (landline and cell) sample
design and included an oversample of 16-39 year olds. A total of 7,509 interviews were
conducted with persons 16 years of age or older living in the United States. Interviewing
began on July 12, 2012, and ended on November 18, 2012. The samples were combined
and weighted to produce national estimates of the target population. This report presents
detailed information on the survey methodology, as well as the full survey instrument.
17. Key Words
18. Distribution Statement
Bicyclist, Pedestrian, Safety,
Methodology
This document is available to the public from the
National Technical Information Service at
www.ntis.gov
19. Security Classif. (of
this report)
.
20. Security Classif. (of
this page)
21. No. of
Pages
Unclassified
Unclassified
9
i
22. Price
Table of Contents
1. Introduction ...................................................................................................................... 1
2. Sample Construction ........................................................................................................ 1
2.1 Stratification............................................................................................................. 1
2.2 Landline Random Digit Dialing (RDD) Sample ..................................................... 2
2.3 Oversample for 16- to 39-Year-Olds ....................................................................... 3
2.4 Sample of Cellular Telephone Numbers .................................................................. 3
2.5 Sampling Cell-Mostly Households .......................................................................... 3
3. Questionnaire Development............................................................................................. 4
3.1 Cognitive Testing ..................................................................................................... 4
3.2 Survey Pretest .......................................................................................................... 5
4. Survey Administration ..................................................................................................... 6
4.1 Advance Letter ........................................................................................................ 6
4.2 Calling Protocol ....................................................................................................... 7
4.3 Spanish Language Interviews .................................................................................. 7
4.4 Answering Machines ............................................................................................... 8
4.5 Monitoring of Telephone Interviewers .................................................................... 8
4.6 Refusal Conversion .................................................................................................. 9
4.7 Field Outcomes ........................................................................................................ 9
5. Response Rates ................................................................................................................ 9
6. Weighting and Estimation.............................................................................................. 10
6.1. Design Weights ..................................................................................................... 10
6.2 Adjusting the Sampling Weights of Dual (Landline/Cell) Users in the Two Frames ...... 12
6.3 Raking Weights...................................................................................................... 13
6.4 Final Weights ......................................................................................................... 13
6.5 Note on Weight Trimming ..................................................................................... 14
6.6 Estimation .............................................................................................................. 18
7. Precision of Sample Estimates ....................................................................................... 19
7.1 Sampling Error ....................................................................................................... 19
7.2 Estimating the Population Variance....................................................................... 20
7.3 Estimating Design Effects...................................................................................... 20
7.4 Testing for Statistical Differences ......................................................................... 24
8. Nonresponse Bias Analysis ........................................................................................... 28
Appendices
Appendix A. Disposition Reports ................................................................................... A-1
Appendix B. Survey Instrument ...................................................................................... B-1
ii
1. Introduction
The goal of the 2012 National Survey of Bicyclist and Pedestrian Attitudes and Behavior (NSBPAB)
was to obtain a “snapshot” of the attitudes and behaviors with regards to bicycling and pedestrian
activities of the U.S. population using a telephone survey of respondents aged 16 years and older.
The previous administration of the NSBPAB was conducted in 2002. Only surveys based on
probability samples can be used to create mathematically sound statistical inferences about a larger
target population. Most statistical formulas for specifying the sampling precision (estimates of
sampling variance), given particular sample sizes, are premised on simple random sampling.
However, random sampling requires an enumeration of all of the elements in the population. Since
no enumeration of the total population of the United States (or its subdivisions) is available, all
surveys of the general public are based upon complex sample designs that may employ stratification
and two or more stages of sampling.
A sampling design using geographic stratification (NHTSA Region), an oversample of young drivers,
sampling frames of households with landlines and cell phones, together with an overall sample size of
7,500 was developed and implemented for this survey. The final sample consisted of 7,509
respondents, which included an oversample of 508 participants ages 16-39, with 35.6 percent of
respondents coming from cell phone only or cell phone mostly households. Weights were developed
to yield national estimates of the target population within specified limits of expected sampling
variability. This report describes the methods of sample construction and survey administration, and
shows the sample dispositions for each of the three samples and computation of weights.
2. Sample Construction
The 2012 National Survey of Bicyclist and Pedestrian Attitudes and Behavior, like the 2002 survey,
was conducted by telephone. Hence, the study procedures called for the construction of a national
sampling frame of telephone households from which a random population sample could be derived.
For the selection of the sample, two sampling frames were employed, the landline RDD sampling
frame and the cell phone sampling frame.
The procedure for developing a population-based sample for this telephone survey in each of the two
frames involved four stages. The first stage sample involved using a population-based sample
allocation, distributed in proportion to the geographic distribution of the target population according
to the most recent Census estimates. The second stage employed a systematic selection of assigned
telephone banks with the geographically stratified first stage sample design. The third stage used a
random digit dialing (RDD) sampling of telephone households within the telephone banks selected in
the second stage. The fourth stage required the identification and systematic selection of one eligible
respondent within each sampled household so that the household sampling frame yielded a
representative sample of the eligible population. These procedures yielded national estimates of the
target population, with specified limits of expected sampling variability, from which valid
generalizations can be made to the general public.
2.1. Stratification
Both the landline and cell phone samples were national probability samples of telephone blocks from
each sampling frame, and were stratified based on NHTSA region. The target population specified
for this study was people 16 and older in the United States. Consequently, the initial stage in the
construction of this sample required the development of a national probability sample of the noninstitutionalized adult population of the United States.
The estimated distribution of the population by stratum was calculated on the basis of the U.S. Census
1
Bureau’s 2010 Census. The population estimates were taken for the population age 16 and older.
Based on these Census estimates of the geographic distribution of the target population, the total
sample was proportionately allocated by stratum.
The geographic location of the sampled hundreds banks in list-assisted RDD sample was based on the
dominant ZIP code for listed numbers within the bank. Since there are no listed numbers for cell
phones, the geographic location assigned to cell phone banks was based on the address of the billing
center for each user. This leads to a significant misclassification of the location of cell phone
households at the community level, but very little at the State level since billing centers are located in
the same State as the household being served. Hence, the geographic stratification by NHTSA region
was effective for both the landline and cell phone components of the dual frame design.
Figure 2.1. NHTSA Regional Population for Ages 16+: 2010
Population
Proportion
Region I
Region II
Region III
Region IV
Region V
Region VI
Region VII
Region VIII
Region IX
Region X
CT, ME, MA, NH, RI, VT
NJ, NY, PA
DE, DC, MD, VA, WV
AL, FL, GA, KY, MS, NC, SC, TN
IL, IN, MI, MN, OH, WI
AR, LA, NM, OK, TX
IA, KS, MO, NE
CO, MT, ND, SD, UT, WY
AZ, CA, HI, NV
AK, ID, OR, WA
243,275,505
11,689,003
22,565,293
23,948,053
48,479,089
40,775,536
29,388,960
10,757,111
8,326,600
37,224,338
10,121,522
100.00%
4.80%
9.28%
9.84%
19.93%
16.76%
12.08%
4.42%
3.42%
15.30%
4.16%
Source: U.S. Bureau of the Census, 2010 Census Demographics by State
2.2. Landline Random Digit Dialing (RDD) Sample
Once the sample was geographically stratified with sample allocation proportionate to population
distribution, a sample of assigned telephone banks was randomly selected from an enumeration of the
Working Residential Hundred Blocks within the active telephone exchanges within the region. The
Working Hundreds Blocks were defined as each block of 100 potential telephone numbers within an
exchange that included one or more residential listings.
A two-digit number was randomly generated by computer for each Working Residential Hundreds
Block selected. This is known as list-assisted random digit dialing (RDD). Every telephone number
within the Working Residential Hundreds Block has an equal probability of selection, regardless of
whether it is listed or unlisted.
The RDD sample of telephone numbers was dialed to determine which numbers were working
residential household telephone numbers. Non-working numbers and non-residential numbers were
immediately replaced by other RDD numbers selected within the same stratum in the same fashion as
the initial number. Ineligible households (e.g., no eligible respondent in the household, language
barriers) were also replaced. Non-answering numbers were not replaced until the maximum number
of call attempts was reached. However, one or more open numbers per case was permitted in order to
permit the data collection to be completed within a reasonable period.
The systematic dialing of those numbers to obtain a residential contact yielded a probability sample of
2
landline telephone households.
2.3. Oversample for 16- to 39-Year-Olds From the Landline Frame
The population prevalence of the target age group 16-39 years old is not large enough to generate the
desired sub-sample size, given a total sample of 7,509 for the survey. Based upon the 2010 Census
approximately 34 percent of the U.S. population is between 16 and 39 years old. However, when
standard RDD sampling with landline telephones was conducted for the 2012 NSBPAB, less than 18
percent of the final sample was between 16 and 39. This is due to the rise in cell phones among those
under 39 as well as the fact that it is more difficult to survey people in the 16-20 age group, who may
be under-represented because they live in a group quarters (e.g., dormitory) setting. Hence, a simple
proportionate sample of the adult population would not meet the needs of this study design. The 16to 39-year-old age group is of particular interest to NTHSA, and this required a boost in the numbers
of respondents who fell into this age range. Consequently, persons in age groups 16-39 were oversampled.
Although the dual frame sample could correct the underrepresentation of the 16- to 39-year-old
cohort in total sample, a small oversample was employed to ensure a large subsample of 16- to 39year-olds in the final sample. Hence, an independent landline sample was drawn and a separate script
was programmed to screen for households with 16- 39-year-olds present and select one of the ageeligible persons in the household for the interview. We obtained 740 interviews with 16- to 39-yearolds out of 4,789 in the cross-sectional landline sample, 508 from the landline oversample, and 1,154
from the cell phone sample. This brought the sample size of completed interviews for this 16- to 39year-old age group to 2,402 or 32 percent of the total sample.
2.4. Sampling of Cellular Telephone Numbers
Although list-assisted landline RDD sampling provides only a small coverage error for telephone
households within landline banks, the restriction of the sampling frame to only landline banks
introduces a much more serious coverage error in general population surveys. The increasing
percentage of households that have abandoned their landline telephones for cell phones over the past
decade has significantly eroded the population coverage provided by landline-based surveys. Cell
phone only households are not covered by current RDD landline sampling procedures, which exclude
telephone exchanges and 1,000 banks used exclusively for cell phones. Furthermore, these are some
of the same groups that are increasingly under-represented in current RDD landline telephone surveys
due to differential non-response, so it is very important to include cell phone only households in the
sample.
Landline only adults were covered by the landline sample frame as were adults that have dual
telephone service – landline and cellular telephone service. Although cell phone only households
were excluded from landline samples, dual service respondents were underrepresented in landline
surveys. As discussed below, some dual telephone service households were much more likely to be
reached in a cell phone sample than in a landline RDD sample.
Regardless of the specific type of dual frame design selected for a study, a cell phone only segment
was required. Due to the significantly higher cost of the cell phone interviews compared to the
landline interviews, dual frame surveys are usually designed with optimal allocation of sample
between the landline and cell phone strata, rather than simply using a proportional allocation.
2.5. Sample of Cell-Mostly Households
Cell-mostly households appeared in both the landline and cell phone samples. In total, 2,212
interviews were completed with the cell phone sample. Of these, 1,669 were completed with cell
3
phone only households, meaning no landline was present in the household, and 543 were completed
with cell phone mostly households, or households who receive all or almost all calls on their cell
phone despite having a working landline in their home as well. In the landline sample, 1,085
interviews were completed with households who identified themselves as cell phone mostly. The
inclusion of the cell phone mostly households from the cell phone sample reduces the cost differential
between landline and cell phone interviews while providing better coverage of populations
underrepresented, if not excluded, from landline samples.
Figure 2.2. Sample Counts by Age from the Two Frames
Age
Sample Type
Age 16-39 Age 40 + Unknown
Landline RDD
Cell Phone RDD
Landline Oversample
TOTAL
TOTAL
740
4,001
48
4,789
1,154
1,048
10
2,212
508
0
0
508
2,402
5,049
58
7,509
3. Questionnaire Development
3.1Cognitive Testing
Although the 2012 questionnaire was largely based on the 2002 questionnaire for consistency and
comparability across the two surveys, there were enough significant changes to warrant cognitive
testing of the 2012 survey instrument. Consequently, cognitive interviews were conducted using the
2012 survey instrument to measure how respondents might interpret and respond to new or revised
questions. The cognitive testing process involved a series of standardized probes that were
introduced at specified points in the draft questionnaire. The objective was to identify any questions
or response categories which could pose problems for respondents with encoding, recall or the
decision process prior to the full implementation of the survey.
A total of nine one-on-one cognitive interviews were conducted on March 16, 2012, with persons
selected from the general public. The cognitive interviews were conducted at the Cognitive Interview
Lab at Abt Associates in Bethesda, MD. These interviews were conducted by professional
interviewers under the direction of Johnny Blair, the Director of the Abt Cognitive Lab. The COTR
and two other DOT staff members came to observe four of the nine interviews from a separate
viewing room which had TV monitors set up for this purpose.
The cognitive testing of the survey instrument was performed by adding probes at various points
during the interview, designed to measure respondents’ understanding of the questions and the
response options. Illustrative probes used in the cognitive testing included the following:
•
•
•
•
•
•
•
•
Please restate this question in your own words
What does ……mean to you?
Are there any other answer categories I should have provided?
Is there another term we should use?
What type of answer did you think I was looking for?
Was this question difficult to answer?
How did this question differ from a previous question?
What part of the question did you focus on when you came up with your answer?
4
Respondents indicated a basic level of understanding of the questions asked and were able to
accurately rephrase questions when probed. The same was true when respondents were asked if they
understood specific words and phrases. Overall, the survey instrument worked very well among
respondents. The majority of revisions which were made as a direct result of the cognitive testing
included adding new response options to specific questions. For example, “Rental Spot” was added
to the Origin and Destination question for bicyclists.
3.2 Survey Pretest
A survey pretest was conducted on July 11, 2012, with 15 respondents. The pretest served as a “dress
rehearsal” and tested the survey systems, in addition to testing the instrument and CATI
programming. The pretest of the survey instrument also evaluated the wording of questions and
response categories in terms of clarity and confusion for respondents via telephone administration;
assessed the flow of the interview, including question sequencing and skip patterns; determined the
time required to administer the questionnaire over the telephone; helped gauge item non-response to
sensitive questions; ensured that a smooth interview occurred with previous information guiding later
questions; ensured random rotation of specified questions; checked that invalid responses were not
entered; and reviewed and evaluated the full range of procedures.
No significant changes to the questionnaire were made as a result of the pretest, and the main data
collection was approved to go forward the following day.
5
4. Survey Administration
4.1. Advance Letter
An advance letter was sent out to respondents who had an address match from Survey Sampling Inc.
(SSI). The advance letter did not have an impact on the cooperation, response rate, or refusal rate,
and was discontinued after being mailed out to approximately 10,000 households. The letter is shown
in Figure 4.1 below.
Figure 4.1. Advance Letter to household with an Address Match
<>
NAME
ADDR1
ADDR2
CITY, ST ZIP
Dear NAME:
I am contacting you on behalf of the National Highway Traffic Safety Administration (NHTSA) of
the U.S. Department of Transportation. NHTSA has contracted with Abt SRBI to conduct a national
study on bicyclist and pedestrian behavior. I have sent this letter to alert you that an interviewer from
Abt SRBI will be calling in the near future to request that a member of your household participate in
the survey. NHTSA is conducting the survey in order to identify current issues and obstacles that
people have in being able to walk and bicycle outdoors. The information obtained will be used to
provide guidance to programs across the country that seek to improve pedestrian and bicyclist safety.
The interviewer will ask to interview one member of your household that the interviewer will select
randomly. This random selection is necessary in order to produce national estimates. The interview
takes only about 20 minutes to complete. It is voluntary and the person being interviewed doesn’t
have to answer any questions that he or she doesn’t want to answer. The interviewer will not collect
information that could be used later to identify the person who provided the responses.
NHTSA has placed a link on its web site (www.nhtsa.gov/pedbikesurvey) where prospective survey
participants can confirm this is a government-sponsored survey. The survey has been reviewed and
approved by the U.S. Office of Management and Budget. The OMB control number is 2127-0684.
Your household’s participation in this survey would be a big help to NHTSA in its continuing efforts
to improve safety for bicyclists and pedestrians, as well as to the many others across the country who
use this information to design their own safety programs and community improvements. I hope you
will agree to participate.
Sincerely,
Paul B. Schroeder
Vice President
Abt SRBI, Inc
6
4.2. Calling Protocol
Initial telephone contact was attempted during the hours of the day and days of the week that have the
greatest probability of respondent contact. The primary interviewing period was from 5:30 p.m. to
9:30 p.m. on weekdays, 9 a.m. to 9:30 p.m. on Saturdays, and from 10 a.m. to 9:30 p.m. on Sundays
(all times are listed as local times). Since interviewing was conducted across time zones, the
interviewing shift lasted until 12:30 a.m. Eastern (9:30 p.m. Pacific Time).
If the interview was not conducted at the time of the initial contact, the interview was rescheduled at a
time convenient to the respondent. Although initial contact attempts were made on evenings and
weekends, daytime interviews were scheduled when necessary. If four telephone contacts on the
night and weekend shifts did not result in a completed interview, the fifth contact was attempted on a
weekday during the daytime.
Interviewers attempted a maximum of 10 calls to each landline telephone number in order to reach a
person within the household. When the household was reached, the interviewer asked to speak to
someone 16 years old or older. If there was more than one person in the household who was 16 years
old or older, one of the eligible adults was selected by designating the adult who had the most recent
birthday, or who was going to have the next birthday (this condition was randomized within the CATI
program), as the target respondent. When the target respondent was reached, but an interview at that
time was inconvenient or inappropriate, interviewers set up appointments with respondents. When
contact was made with the household, but the target respondent was unavailable, interviewers probed
for appropriate callback times for an appointment. After a household was reached, the maximum
number of call attempts was raised to 15.
For cell phone respondents, interviewers attempted a maximum of five calls to each number for it to
be deemed a permanent no answer. If contact was made with a respondent, a maximum of 10 call
attempts were made. Unlike the landline numbers, cell phones were treated as a personal device,
hence there was no respondent selection performed. If the person answering the cell phone was 16
years old or older, they were deemed eligible for the interview. Prior to asking the person’s age, all
cell phone respondents were first asked if they were currently driving and if they were in a safe place
to talk. If the respondent was driving or in an unsafe place to use a cell phone, the interviewer
thanked the respondent and hung up the phone, noting the time of the call so the respondent would
not be reached at the same time on the subsequent attempt. Respondents who completed the
interview on their cell phones were offered a $10 remuneration to account for limited calling plans.
4.3. Spanish Language Interviews
A Spanish language version of the survey instrument was developed in order to eliminate language
barriers for a small proportion of the U.S. adult population. The questionnaire was translated into
Spanish by a professional translation firm. The Spanish questionnaire was then reviewed next to the
English questionnaire by a different translator and checked for errors. Any translations that were not
comparable were revised to be in line with the intent of the English questionnaire.
If the interviewer encountered a language barrier during the initial contact, either with the person
answering the phone or with the designated respondent, the interviewer thanked the person and
terminated the call. If the case was designated as Spanish language, it was turned over to the next
available Spanish-speaking interviewer.
All households which were designated as “Foreign Language-Spanish” were assigned to a Spanishspeaking interviewer. These bilingual interviewers re-contacted each Spanish-speaking household to
screen for eligibility and conducted the interview with the target respondent. Less than 3 percent
(2.4%) of the completed interviews were conducted in Spanish.
7
4.4. Answering Machines
Abt SRBI implemented a plan for increasing participation from persons in households where
telephone contact was made with an answering machine or voice mail. The strategy for handling
answering machines with a 15-call protocol needed to balance the objectives of reaching the
household and avoiding unnecessary annoyance of the household. Abt SRBI was responsible for
maintaining a toll free number where the respondent could call, as well as placing a description of the
study on the Abt SRBI website for respondents. In addition, NHTSA placed a statement on its
website that the prospective survey participant could access by Internet to verify the legitimacy of the
survey. In order to evaluate the value of these steps, survey respondents were asked as part of the
interview whether they used the toll free number or the NHTSA Web site.
Figure 4.2. Final Voicemail/Answering Machine Script
I am calling on behalf of the U.S. Department of Transportation. We are conducting a
national study on bicycle and pedestrian safety. The interview will only take about 20
minutes. This is not a sales call. Please call us at 1-866-780-8528 between 5 p.m. and 12
a.m. Eastern time. Ask for study number 5432. For more information about the study please
visit www.nhtsa.gov/pedbikesurvey. Thank you very much.
4.5 Monitoring of Telephone Interviewers
Each interviewer was monitored throughout the course of the project. The monitor evaluated the
interviewer on his or her performance. The monitor discussed any problems that an interviewer was
having with the shift supervisor. All interviewers on the project underwent two types of monitoring.
The study monitor sat at a computer where he/she could see what the interviewer had recorded, while
audio-monitoring the interview. The audio-monitoring allowed the supervisor to determine the
quality of the interviewer's performance in terms of:
1) Initial contact and recruitment procedures;
2) Reading the questions, fully and completely, as written;
3) Reading response categories, fully and completely, (or not reading them) according to study
specifications;
4) Whether or not open-ended questions were properly probed;
5) Whether or not ambiguous or confused responses were clarified;
6) How well questions from the respondent were handled without alienating the respondent or
biasing his/her response;
7) Avoiding bias by either comments or vocal inflection;
8) Ability to persuade wavering, disinterested or hostile respondents to continue the interview;
and
9) General professional conduct throughout the interview.
The supervisor also monitored the interviewer's recording of survey responses; the supervisor's screen
emulated the interviewer's screen. Consequently, the supervisor was able to see whether the
interviewer entered the correct code, number or verbatim.
4.6 Refusal Conversion
The process of converting terminations and refusals, once they had occurred, involved the following
steps. First, there was a diagnostic period, when refusals and terminations were reported to the
8
Operations Manager on a daily basis. The Project Director reviewed these as well to see if anything
unusual was occurring. Second, after enough time had passed to see enough refusals and
terminations, the Project director and his staff developed a refusal conversion script. Third, the
refusal conversion effort was fielded with re-interview attempts scheduled about a week after the
initial refusal. Fourth, the Project Director and Operations Manager received the outcomes of the
refusal conversion efforts. Minor revisions to the script and the procedures were made, as needed.
4.7 Field Outcomes
Survey data collection by the Federal Government requires prior approval by the Office of
Management and Budget (OMB). NHTSA published a Notice in the Federal Register soliciting
comments on the information collection. The Notice appeared in the Federal Register on June 13,
2011 (Vol. 76, No. 113, pp 34290-34291). NHTSA then submitted the request for data collection to
OMB. OMB approved the information collection on July 2, 2012, assigning it the OMB number
2127-0684 with an expiration date of July 31, 2015. The Abt SRBI IRB (FWA 0000580) reviewed
and approved this study on June 9, 2012.
The field interviewing for the study commenced on July 12, 2012, following the training of the field
interviewers, and was completed on November 18, 2012. There was a period of interruption from
October 30, 2012, through November 8, 2012, to reduce the burden on respondents who were
receiving many phone calls from political campaigns, since 2012 was a Presidential election year.
This extended the field period by almost 2 weeks, however, it was warranted given the respondent
burden concerns.
A total of 7,509 interviews were conducted for the survey, including 4,789 interviews for the landline
RDD cross-section, 2,212 for the cell RDD sample, and 508 for the 16-39 year old landline
oversample. The average interview length for the interview was 17.9 minutes for the landline RDD
cross-section, 21.7 minutes for the cell phone RDD, and 18.9 minutes for the landline RDD
oversample.
5. Response Rates
Response rates were calculated independently for each sample: landline cross-section, cell phone
sample, and the landline oversample. For the purposes of analysis and weighting, cases from the
oversample who reported they were over 39 years old in the demographics were moved to the
landline cross-section sample. However for the purposes of calculating response rate for each
sample, these cases were left in the oversample, hence the sample totals in Figure 5.1 do not match
the totals for sample type which are shown elsewhere in this report. For sample dispositions and
details on how the response rate was calculated please refer to Appendix A: Sample Dispositions.
Figure 5.1 Response Rates by Sample Type
Total Numbers
Sample Type
Dialed
Final N
Response Rate
Landline Cross-section
88,655
4,503
25.32%
Cell Phone
46,998
2,212
13.81%
Landline Oversample
57,386
794
22.99%
6. Weighting and Estimation
In order to produce population-based estimates while conducting statistical analyses on the data, each
respondent in the survey is assigned a sampling weight. The weights for the 2012 NSBPAB were
calculated in three steps: 1) calculating design weights for the cell sample, landline sample, and the 16-39
9
landline oversample, 2) adjusting the weights of persons who are in both the landline frame and the cell
frame, and 3) population calibration (i.e., post-stratification and raking of weights).
6.1. Design Weights
The first stage in the weighting process involved creating sampling weights that correct for
disproportionate probabilities of selection, or design weights. The design weight for a sampling unit is
the inverse of the probability that the particular unit is drawn into the sample. For the 2012
NSBPAB, the design weight was calculated using the following steps:
Landline Sample
The initial design weight is the inverse of the probability of selection of the landline telephone
number of the responding household. Since the sample of telephone numbers is stratified by the ten
NHTSA regions, the sampling weights are computed within each stratum.
Let N lh be the number of phone numbers in phone banks with one or more directory-listed landline
phone numbers in stratum h . Let nlh be the numbers of phone numbers selected from these banks
and dialed. The sampling weight for households selected in that stratum is
Wlh =
N lh
nlh
In addition to the sample of nlh telephone numbers, an additional sample of noh telephone numbers
was selected from the population of telephone numbers to screen and identify households with
persons who are 16-39 years old. This means persons who are 16-39 had two chances of selection.
Either they could be selected in the landline cross-section sample or the oversample. Based on this
probability of selection, the design weight of households with 16- to 39-year-olds in stratum h is
Wloh =
N lh
nlh + noh
Hence, there are two sets of weights for selected household in each landline stratum. One set of
weights for those households with 16- to 39-year-olds and a second set for those households having
persons outside this age range.
Cell Phone Sample
If the number of cell telephone numbers selected from a population of N ch numbers is nch then the
design weight for persons selected through cell phone sampling stratum h is
Wch =
N ch
nch
The sampling weights for households selected in the landline frame and persons selected from the cell
frame are given in Figure 6.1.
10
Figure 6.1. Frame and Sample Counts by NHTSA Region
Landline Frame
Design weight
(W1)
Sample size
NHTSA
Region
Frame
(NL)
Cell Frame
Not
Base
Over eligible Eligible
sample sample for over for over
(nL)
(nO)
sample sample*
Frame
(NC)
Sample
size
(nC)
Design
weight
(W1)
1
13,867,300
9,153
4,869
1515.06
988.97
19,962,500
1,346
14830.98
2
39,450,100
26,274
13,848
1501.49
983.25
56,538,300
3,843
14712.02
3
28,598,600
19,417
10,038
1472.86
970.93
44,022,600
3,046
14452.59
4
41,721,700
28,113
14,645
1484.07
975.76
63,098,400
4,369
14442.30
5
51,374,600
34,322
18,034
1496.84
981.26
74,660,800
5,053
14775.54
6
32,669,700
23,242
11,467
1405.63
941.25
61,579,200
4,166
14781.37
7
15,590,500
10,625
5,473
1467.34
968.47
24,458,000
1,667
14671.87
8
11,159,300
7,595
3,917
1469.30
969.36
18,649,400
1,261
14789.37
9
37,254,200
25,486
13,077
1461.75
966.06
59,223,400
3,961
14951.63
10
13,194,400
8,819
4,632
1496.13
980.92
19,610,800
1,288
15225.78
*Include eligible from base sample and oversample.
Multiple-Landline Telephone Households
The design weights of households with multiple landline telephone numbers are adjusted to
compensate for the higher probability of selection into the sample. The probability of selecting a
household in an RDD sample is proportional to the number of distinct telephone numbers associated
with the household. The weight adjustment alters the design weight by dividing the weight by the
number of landline telephones in the household, based on self-report. The multiple phone adjustment
is capped at three to avoid extreme weights. The multiple phone adjustment was not performed for
households in the cell phone frame.
Selection of an Eligible Person within the Household Selected in the Landline Sample
For the landline sample (including the oversample), one member (age 16 or older) from each
household was randomly selected to take the survey. The sampling weight for the person selected
within a household is equal to the number of eligible adults in the household. The within household
subsampling adjustment is capped at three to avoid extreme weights. No within household selection
was conducted for cell phones.
Therefore the overall person weight for persons selected in the ith household in stratum h landline
sample is
Wlhi = Wlh
mhi
.
Ahi
Where mhi is the number of persons in the household and Ahi
lines in the household.
11
is the number of landline telephone
6.2 Adjusting the Sampling Weights of Dual (Landline and Cell) Users in the Two Frames
The 2012 NSBPAB was a partial overlapping landline and cell dual frame where
1. Landline-only (no working cell phone) respondents and dual users were interviewed in the
landline sample;
2. Cell-only (does not have landline) respondents were interviewed in the cell phone sample;
and
3. Cell-mostly respondents were interviewed in either the landline or the cell phone sample.
This group makes up the overlap of the two sample frames.
Cell only respondents can only come from the cell phone sample, but cell-mostly respondents can
come from the landline or the cell phone sample. Therefore, we adjust the cell-mostly respondents to
account for multiple frames. The weight adjustment is done in two steps.
To adjust the sampling weight for nonresponse the following procedure was carried out.
1) The design weights of both landline and cell samples are each adjusted such that the weighted
estimates equal the population estimates for each phone status category based on the latest
estimates from the National Health Interview Survey (NHIS). The counts in each sample and
the NHIS estimates are shown in Figure 6.3.
2) Then the weights for the cell-mostly category were adjusted by a factor. The cell-mostly
households comprise the only overlapping category in that these households were drawn from
both the landline frame and the cell frame. This factor is based on the effective sample sizes
n1 / deff 12
of this group from the two frames. The adjustment factor is c =
,
n1 / deff 12 + n2 / deff 22
[
]
= n × ∑ wi2 × ∑ wi is a measure of variability of respondent level weights
(wi) and n is the sample size for the survey. The landline design weight is multiplied by c,
where 0 < c < 1 and the cell phone design weight by 1-c.
where deff
2
−2
Figure 6.3 Sample Counts by Sample Frame and Household Type
Phone status adjustment
Sample size
(PHADJ)
Phone status
Landline
Cell
NHIS Jangroup (g)
(nL)
(nC)
Jun 2012 1
Landline*
Cell*
Cell-only
1,669
34.0%
Cell-mostly
1,085
543
17.6%
Dual user
Landline only
3,291
921
38.7%
7.8%
*The NHIS percentage are scaled to one million to avoid extremely small values for the adjustments.
1
Composite
weight (c)
1.0000
0.3056
0.0000
0.0000
Blumberg SJ, Luke JV. Wireless substitution: Early release of estimates from the National Health Interview
Survey, January–June 2012. National Center for Health Statistics. December 2012. Available from:
http://www.cdc.gov/nchs/nhis.htm.
12
6.3 Raking Weights
As the final weighting step, the raking procedure aligns the marginal distribution of respondents on
certain socio-demographic characteristics. For the 2012 NSBPAB these include: 1) NHTSA region
by sex, 2) age group by race/ethnicity, 3) sex by age group by educational attainment, 4) sex by
race/ethnicity, 5) NHTSA region by age group, and 6) age group by sex. In the first iteration, the
procedure matches the distribution of the first demographic variable to the population benchmark,
recalculates cell counts and creates new totals. The second iteration matches the distribution of the
second demographic variable to its population benchmark using the new cell counts from the first
iteration and calculates new totals. The iteration continues alternating between the distributions until
the adjusted distributions converge with the population benchmark totals. At this point a final set of
raked weights are produced. The population data is based on the 2011 American Community Survey
(ACS). The sample distributions prior to and after raking adjustments, as well as the population
distributions are listed in Figures 6.4-6.9.
6.4 Final Weights
The final weight can be represented as follows:
Landline:
FINAL_WT = W1×WWHH/WPHONES×PHADJ×(1-C)×RAKEADJ
Cell:
FINAL_WT = W1×WWHH/WPHONES×PHADJ×C×RAKEADJ
13
6.5. Note on Weight Trimming
We evaluated the weights to determine whether weight trimming was needed. First we calculated the
coefficient of variation for the weights before weight trimming. Second, we trimmed weights greater
than 10 ∑
⁄ back to this cutoff. The non-trimmed weights were proportionally increased to
offset the trimmed weights. This process was repeated until no weights met the criteria. Finally we
compared the coefficients of variation before and after weight trimming.
CV of weights prior to weight trimming = 65.65
CV of weights after weight trimming = 65.47
Since the variation in the weights was not considerably improved, no weight trimming was
conducted.
We also looked at the distribution of final weights. Any weight larger than the median weight plus 6 times
the interquartile range is declared as large and would need to be trimmed. In this survey, there were no
weights larger than median + 6 times the interquartile range. Therefore, no weights were declared as
outliers and no trimming was performed.
Population Control Totals for Raking Weights (Figures 6.4 – 6.9)
Figure 6.4. Dimension 1: NHTSA Region by Sex
Before After raking
NHTSA
2011 ACS 16+ Sample
size
raking (%)
(%)
Region Sex
Pop
1
Male
220
2.79
2.37
Female
188
2.54
2.41
2
Male
15,864,597
562
7.18
6.42
Female 17,176,251
593
7.57
7.03
3
Male
12,018,362
402
5.22
4.82
Female 12,912,373
411
5.09
5.31
4
Male
17,242,256
518
7.17
6.90
Female 18,500,977
512
6.96
7.61
5
Male
19,958,556
629
8.39
8.09
Female 21,065,776
634
8.56
8.55
6
Male
14,645,281
408
5.60
5.80
Female 15,284,685
394
5.33
6.36
7
Male
212
2.93
2.66
Female
198
2.86
2.66
8
Male
127
1.62
1.99
Female
167
2.14
2.04
9
Male
17,607,663
476
6.49
7.29
Female 18,052,242
451
6.09
7.17
10
Male
201
2.59
2.32
Female
206
2.87
2.18
14
Raking
Ratio
0.85
0.95
0.89
0.93
0.92
1.04
0.96
1.09
0.96
1.00
1.04
1.19
0.91
0.93
1.22
0.96
1.12
1.18
0.90
0.76
Figure 6.5. Dimension 2: Age Group by Race/Ethnicity
Sample
Before
Age
2011 ACS
size
raking (%)
group
Race/Ethnicity 16+ Pop
16-34
Hispanic
16,684,652
332
4.97
NH white
46,324,629
1091
15.37
NH black
11,118,074
210
2.97
NH other
7,096,915
185
2.66
44-54
Hispanic
13,244,834
293
4.52
NH white
55,147,485
1795
24.97
NH black
10,374,220
271
3.63
NH other
6,714,558
206
2.84
55+
Hispanic
6,403,554
162
2.19
NH white
61,140,897
2539
30.63
NH black
7,192,448
241
2.98
NH other
4,713,328
184
2.27
15
After raking
(%)
Raking
Ratio
6.29
19.38
1.27
1.26
4.46
1.50
2.87
1.08
5.68
1.26
22.23
0.89
4.08
1.12
2.73
0.96
2.70
1.23
24.71
0.81
2.93
0.98
1.93
0.85
Figure 6.6. Dimension 3: Sex by Age Group by Educational Attainment
Before After raking Raking
Age
Educational 2011 ACS 16+ Sample
raking (%)
(%)
Ratio
Sex
group
attainment
Pop
size
Male 16-24
20,354,986
406
5.95
8.27
1.39
25-34 LT HS
2,893,738
30
0.50
1.10
2.20
HS grad
5,834,166
114
1.47
2.34
1.59
Some college
6,391,960
137
1.92
2.60
1.35
College grad
5,772,478
236
3.32
2.44
0.73
35-44 LT HS
2,874,587
37
0.57
1.10
1.93
HS grad
5,670,566
95
1.35
2.23
1.66
Some college
5,741,508
169
2.26
2.38
1.05
College grad
6,021,574
286
3.37
2.55
0.76
45-64 LT HS
5,267,389
102
1.57
1.95
1.24
HS grad
11,929,090
335
4.84
4.87
1.00
Some college
11,413,334
377
5.47
4.64
0.85
College grad
11,726,552
593
8.08
4.93
0.61
65+
LT HS
3,655,173
91
1.01
1.43
1.42
HS grad
5,215,592
230
2.59
2.14
0.83
Some college
3,988,278
213
2.36
1.63
0.69
College grad
5,057,203
304
3.35
2.08
0.62
Female 16-24
19,328,937
389
5.81
7.85
1.35
25-34 LT HS
2,149,472
33
0.54
0.84
1.56
HS grad
4,272,844
113
1.46
1.71
1.17
Some college
6,892,751
136
1.86
2.80
1.51
College grad
7,332,937
224
3.12
3.03
0.97
35-44 LT HS
2,281,688
31
0.51
0.87
1.72
HS grad
4,688,678
113
1.58
1.89
1.20
Some college
6,549,478
151
2.03
2.68
1.32
College grad
6,999,631
278
3.42
2.89
0.85
45-64 LT HS
4,808,788
87
1.34
1.87
1.40
HS grad
12,149,504
365
5.14
4.91
0.96
Some college
13,515,547
393
5.37
5.52
1.03
College grad
11,908,384
613
8.49
4.91
0.58
65+
LT HS
5,158,470
85
0.92
2.05
2.24
HS grad
8,892,771
238
2.72
3.64
1.34
Some college
5,345,485
230
2.51
2.17
0.87
College grad
4,072,054
275
3.20
1.67
0.52
16
Figure 6.7. Dimension 4: Sex by Race/Ethnicity
Before After raking
2011 ACS
(%)
Sex
Race/Ethnicity
16+ Pop Sample size raking (%)
Male
Hispanic
18,394,192
410
6.07
7.44
NH white
79,256,339
2696
35.02
32.26
NH black
13,384,258
357
4.96
5.41
NH other
8,773,385
292
3.94
3.57
Female
Hispanic
17,938,848
377
5.61
7.23
NH white
83,356,672
2729
35.95
34.07
NH black
15,300,484
365
4.62
6.07
NH other
9,751,415
283
3.82
3.96
Figure 6.8. Dimension 5: NHTSA Region by Age Group
NHTSA
2011 ACS 16+
Region
Age group
Pop
Sample size
1
16-34
3,602,771
106
35-54
4,168,891
132
55+
3,999,126
170
2
16-34
10,491,562
281
35-54
11,523,345
405
55+
11,025,941
469
3
16-34
8,099,818
175
35-54
8,792,382
310
55+
8,038,535
328
4
16-34
11,255,910
249
35-54
12,263,040
341
55+
12,224,283
440
5
16-34
13,176,894
292
35-54
14,259,563
431
55+
13,587,875
540
6
16-34
10,614,904
190
35-54
10,470,195
288
55+
8,844,868
324
7
16-34
4,291,500
92
35-54
4,396,985
134
55+
4,455,481
184
8
16-34
3,500,846
84
35-54
3,378,391
102
55+
2,939,643
108
9
16-34
12,529,124
268
35-54
12,452,551
288
55+
10,678,230
371
10
16-34
3,660,941
81
35-54
3,775,754
134
55+
3,656,245
192
17
Raking
Ratio
1.22
0.92
1.09
0.91
1.29
0.95
1.31
1.04
Before
After
Raking
raking raking (%) Ratio
1.33
1.46
1.10
1.93
1.69
0.88
2.07
1.62
0.78
3.75
4.26
1.14
5.50
4.69
0.85
5.50
4.51
0.82
2.20
3.29
1.49
4.20
3.57
0.85
3.91
3.27
0.84
3.74
4.57
1.22
4.93
4.98
1.01
5.46
4.95
0.91
4.34
5.35
1.23
5.96
5.80
0.97
6.65
5.49
0.83
2.95
4.31
1.46
4.22
4.25
1.01
3.75
3.60
0.96
1.42
1.74
1.22
2.06
1.78
0.86
2.30
1.80
0.78
1.11
1.42
1.28
1.43
1.37
0.96
1.22
1.24
1.01
3.92
5.09
1.30
3.90
5.06
1.30
4.77
4.32
0.91
1.19
1.49
1.25
1.83
1.54
0.84
2.44
1.48
0.61
Figure 6.9. Dimension 6: Age Group by Sex
Before raking After raking
2011 ACS
(%)
(%)
Raking Ratio
Age group
Sex
16+ Pop
Sample size
16-24
Male
20,354,986
406
5.95
8.27
1.39
Female
19,328,937
389
5.81
7.85
1.35
18-34
Male
20,892,342
517
7.22
8.49
1.18
Female
20,648,004
506
6.98
8.39
1.20
35-44
Male
20,308,235
587
7.55
8.25
1.09
Female
20,519,475
573
7.53
8.34
1.11
45-54
Male
21,990,093
706
10.61
8.93
0.84
Female
22,663,294
699
10.28
9.21
0.90
55-64
Male
18,346,272
701
9.36
7.45
0.80
Female
19,718,929
759
10.06
8.01
0.80
65-74
Male
10,474,911
499
5.99
4.26
0.71
Female
12,014,318
503
6.05
4.88
0.81
75+
Male
7,441,335
339
3.32
3.02
0.91
Female
11,454,462
325
3.30
4.65
1.41
6.6 Estimation
For producing population based estimates of population totals, means and proportions, each
respondent is assigned a final sampling weight as described in the previous section. For example, the
estimate of a population proportion of persons responding “yes” to a specific question in the survey
will be estimated as shown below. The estimate is a ratio given by
Yˆ
Pˆ =
Nˆ
where Yˆ is the estimated number of persons who said “yes”, Nˆ is the estimated number of persons
eligible for the survey and Pˆ is the estimated proportion.. The sample was selected independently from
the two strata (Landline frame and Cell frame). The sampling weights of persons who have a probability
of being selected in both samples were adjusted to account for this duplication such that the sum of the
two frame estimates equals the total population size of all dual users. Therefore, the total population
estimate will be the sum of two strata estimates as given below.
Yˆ = Yˆ1+ Yˆ2 ,
Nˆ = Nˆ 1 + N 2 .
The sampling weights that are used to determine the estimated population totals are the final sampling
weights of persons selected in each frame as described under the section on weighting
The variance of Yˆ is V (Y ) = V (Yˆ1 ) + V (Yˆ2 ) and V ( Nˆ ) = V ( Nˆ 1 ) + V ( Nˆ 2 ).
18
7. Precision of Sample Estimates
The confidence interval for an estimate derived from the survey sample is:
⁄
where:
= an estimate of the population proportion;
= is the sampling variance of ; and
⁄2 th percentile of the standard normal distribution (95%:
=
1
⁄
90%: = 10%, = 1.645).
= 5%,
= 1.96;
7.1 Sampling Error
The sampling variance for an estimate is a measure of uncertainty that reflects the fact that the
estimate is derived from a sample drawn from the population. If one were to draw a second sample in
the exact same manner, the estimate would be different from the first simply due to the fact that the
sample contains different members of the population. A third sample would be different from the
first two, and so on. The sampling variance measures how different the estimates would be had
different independent samples been drawn.
The sampling error for a complex survey depends on three things,
the population variance for the characteristic: the sampling variance is higher when there is
a lot of variability in the population (large ) and lower when there is little variability in the
population.
2. n = The sample size: the sampling variance is higher when the sample size is small and lower
when the sample size is large. The sampling variance for estimates of subgroups is based on the
sample size for those subgroups.
3. DEFF = design effect:2 Sampling design features such as stratification, clustering, dual-frame
sampling, and survey weighting all contribute to the sampling variability. The design effect is a
measure of inefficiency (or efficiency) of the complex sample relative to a simple random
⁄ srs .
sample, calculated as
1.
The variances of the estimates from this survey were computed using the SAS SURVEYMEANS
program. The variance of an estimate from the survey is the sum of the variances of the estimates in
the two primary strata which are Landline and Cell frames. The variances of the estimates from the
sample selected in the Landline frame are aggregations of 10 strata variances where each stratum is a
NHTSA region. Similarly, the variances of the estimates in the Cell frame are an aggregation of
variances of estimates within each NHTSA region. The sum of the two frame variances gives the
variance of an overall estimate. The variances are calculated using final sampling weights under the
assumption of sampling with replacement.
We can write the sampling variance of the complex design as:
srs
. Therefore, one can calculate the sampling variance with the population variance (or
⁄
an estimate of the population variance); the sample size; and the design effect.
2
Kish, L. (1965). Survey Sampling, New York: John Wiley & Sons.
19
7.2 Estimating the Population Variance
∑
⁄ . In the case of
The population variance is often estimated from the survey data,
= P×(1-P) and can be estimated from the survey estimate
percentages, the population variance
̂
1
̂ . An alternative is to use the variance estimates based on the percentages presented
in Table 7.1. Rounding the estimated percentage up to the nearest 5 percentage points (e.g., 17% to
20%, 34% to 35%) is a conservative estimate of the population variance. The variance for a
percentage is low when a small percentage of the population has the characteristic (or a large
percentage of the population has the characteristic) and high when the percentage of the population
with the characteristic is equal (50/50).
7.3 Estimating Design Effects
The sampling design impacts the variance for each data item differently. Therefore the design effect
for one survey estimate might be higher or lower than the design effect of another survey estimate.
The design effect will also vary for different subpopulations represented in the sample, such as males
and females. To simplify the calculations of the sampling error, design effect approximations are
presented in Table 7.1. These approximations are based on the average design effect for over 100
data items. All data items are percentages calculated from binary responses (1=yes, 0=no).
In each selected stratum, persons belonging to different domains were identified after selection of the
sample. Stratum 1 has 3 domains, Landline only, Dual users, and Cell mostly. The second frame has
two domains, Cell only and Cell mostly, as shown previously in Figure 6.3. Estimates for these
domains can also be obtained.
We can calculate the variances for some estimates either by using the PROC SURVEMEANS or
using an average design effect based on a selected number of variables for which the variances are
estimated using SAS PROCS SURVEY MEANS (refer to user guide for more details):
PROC SURVEYMEANS;
VAR ;
STRATUM FRAME NHTSAREG;
WEIGHT FINAL_WT;
RUN;
20
Table 7.1. Estimated 95% Error Margins Overall and Various Population Subgroups
DEFF
N
P=
50, 50
45, 55
40, 60
35, 65
30, 70
0.2500
Overall
NHTSA Region
1
2
3
4
5
6
7
8
9
10
Gender
Male
Female
Age group
16 or 17
18 to 24
25 to 34
35 to 44
45 to 54
55 to 64
65 to 74
75 or older
0.2475
0.2400
0.2275
0.2100
25, 75
20, 80
15, 85
10, 90
5, 95
0.1875
0.1600
0.1275
0.0900
0.0475
1.45
7509
1.4%
1.4%
1.3%
1.3%
1.2%
1.2%
1.1%
1.0%
0.8%
0.6%
1.28
1.36
1.43
1.36
1.38
1.44
1.27
1.37
1.38
1.49
408
1155
813
1030
1263
802
410
294
927
407
5.5%
3.4%
4.1%
3.6%
3.2%
4.2%
5.5%
6.7%
3.8%
5.9%
5.5%
3.3%
4.1%
3.5%
3.2%
4.1%
5.4%
6.7%
3.8%
5.9%
5.4%
3.3%
4.0%
3.5%
3.2%
4.1%
5.3%
6.6%
3.7%
5.8%
5.2%
3.2%
3.9%
3.4%
3.1%
4.0%
5.2%
6.4%
3.6%
5.7%
5.0%
3.1%
3.8%
3.3%
3.0%
3.8%
5.0%
6.1%
3.5%
5.4%
4.8%
2.9%
3.6%
3.1%
2.8%
3.6%
4.7%
5.8%
3.3%
5.1%
4.4%
2.7%
3.3%
2.8%
2.6%
3.3%
4.4%
5.4%
3.0%
4.7%
3.9%
2.4%
2.9%
2.5%
2.3%
3.0%
3.9%
4.8%
2.7%
4.2%
3.3%
2.0%
2.5%
2.1%
1.9%
2.5%
3.3%
4.0%
2.3%
3.6%
2.4%
1.5%
1.8%
1.6%
1.4%
1.8%
2.4%
2.9%
1.6%
2.6%
1.43
1.43
3351
4158
2.0%
1.8%
2.0%
1.8%
2.0%
1.8%
1.9%
1.7%
1.9%
1.7%
1.8%
1.6%
1.6%
1.5%
1.4%
1.3%
1.2%
1.1%
0.9%
0.8%
1.24
1.16
1.37
1.43
1.32
1.27
1.40
1.43
140
655
1022
1154
1403
1430
1002
664
9.2%
4.1%
3.6%
3.5%
3.0%
2.9%
3.7%
4.5%
9.2%
4.1%
3.6%
3.4%
3.0%
2.9%
3.6%
4.5%
9.1%
4.0%
3.5%
3.4%
2.9%
2.9%
3.6%
4.5%
8.8%
3.9%
3.4%
3.3%
2.9%
2.8%
3.5%
4.3%
8.5%
3.8%
3.3%
3.2%
2.8%
2.7%
3.4%
4.2%
8.0%
3.6%
3.1%
3.0%
2.6%
2.5%
3.2%
3.9%
7.4%
3.3%
2.9%
2.8%
2.4%
2.3%
2.9%
3.6%
6.6%
2.9%
2.6%
2.5%
2.1%
2.1%
2.6%
3.2%
5.5%
2.5%
2.2%
2.1%
1.8%
1.7%
2.2%
2.7%
4.0%
1.8%
1.6%
1.5%
1.3%
1.3%
1.6%
2.0%
21
Table 7.1. Estimated 95% Error Margins Overall and Various Population Subgroups (Continued)
DEFF
N
P=
50, 50
45, 55
40, 60
35, 65
30, 70
25, 75
0.2500
Race/Ethnicity
Hisp
NH AIAN
NH Asian
NH black
NH white
Educational Attainment
LT HS
HS grad
Some college
Coll grad
Grad school
Driving frequency
Almost every
day/every day
Few days a week
Few days a month
Few days a year
Never/over a year ago
0.2475
0.2400
0.2275
0.2100
0.1875
20, 80
15, 85
10, 90
5, 95
0.1600
0.1275
0.0900
0.0475
1.30
1.26
1.29
1.34
1.42
787
176
203
768
5394
4.0%
8.3%
7.8%
4.1%
1.6%
4.0%
8.3%
7.8%
4.1%
1.6%
3.9%
8.1%
7.7%
4.0%
1.6%
3.8%
7.9%
7.5%
3.9%
1.5%
3.6%
7.6%
7.2%
3.8%
1.5%
3.4%
7.2%
6.8%
3.5%
1.4%
3.2%
6.6%
6.3%
3.3%
1.3%
2.8%
5.9%
5.6%
2.9%
1.1%
2.4%
5.0%
4.7%
2.5%
1.0%
1.7%
3.6%
3.4%
1.8%
0.7%
1.27
1.29
1.28
1.33
1.29
685
1829
2060
1565
1317
4.2%
2.6%
2.4%
2.9%
3.1%
4.2%
2.6%
2.4%
2.8%
3.1%
4.1%
2.5%
2.4%
2.8%
3.0%
4.0%
2.5%
2.3%
2.7%
2.9%
3.9%
2.4%
2.2%
2.6%
2.8%
3.7%
2.3%
2.1%
2.5%
2.7%
3.4%
2.1%
2.0%
2.3%
2.5%
3.0%
1.9%
1.7%
2.0%
2.2%
2.5%
1.6%
1.5%
1.7%
1.8%
1.8%
1.1%
1.1%
1.2%
1.3%
1.44
5309
1.6%
1.6%
1.6%
1.5%
1.5%
1.4%
1.3%
1.2%
1.0%
0.7%
1.41
1.33
1.23
1.32
1063
242
96
744
3.6%
7.3%
11.1%
4.1%
3.6%
7.2%
11.1%
4.1%
3.5%
7.1%
10.9%
4.0%
3.4%
6.9%
10.6%
3.9%
3.3%
6.6%
10.2%
3.8%
3.1%
6.3%
9.6%
3.6%
2.9%
5.8%
8.9%
3.3%
2.5%
5.2%
7.9%
2.9%
2.1%
4.4%
6.7%
2.5%
1.6%
3.2%
4.8%
1.8%
22
Table 7.2. Estimated 95% Error Margins Overall and Various Sample Sizes
P
50, 50 45, 55 40, 60 35, 65 30, 70 25, 75 20, 80 15, 85 10, 90 5, 95
0.2500 0.2475 0.2400 0.2275 0.2100 0.1875 0.1600 0.1275 0.0900 0.0475
DEFF
n
1.45
7500
1.4%
1.4%
1.3%
1.3%
1.2%
1.2%
1.1%
1.0%
0.8%
0.6%
6500
1.5%
1.5%
1.4%
1.4%
1.3%
1.3%
1.2%
1.0%
0.9%
0.6%
5500
1.6%
1.6%
1.6%
1.5%
1.5%
1.4%
1.3%
1.1%
1.0%
0.7%
4500
1.8%
1.7%
1.7%
1.7%
1.6%
1.5%
1.4%
1.3%
1.1%
0.8%
4000
1.9%
1.9%
1.8%
1.8%
1.7%
1.6%
1.5%
1.3%
1.1%
0.8%
3500
2.0%
2.0%
2.0%
1.9%
1.8%
1.7%
1.6%
1.4%
1.2%
0.9%
3000
2.2%
2.1%
2.1%
2.1%
2.0%
1.9%
1.7%
1.5%
1.3%
0.9%
2500
2.4%
2.3%
2.3%
2.2%
2.2%
2.0%
1.9%
1.7%
1.4%
1.0%
2250
2.5%
2.5%
2.4%
2.4%
2.3%
2.2%
2.0%
1.8%
1.5%
1.1%
2000
2.6%
2.6%
2.6%
2.5%
2.4%
2.3%
2.1%
1.9%
1.6%
1.1%
1750
2.8%
2.8%
2.8%
2.7%
2.6%
2.4%
2.3%
2.0%
1.7%
1.2%
1500
3.0%
3.0%
3.0%
2.9%
2.8%
2.6%
2.4%
2.2%
1.8%
1.3%
1250
3.3%
3.3%
3.3%
3.2%
3.1%
2.9%
2.7%
2.4%
2.0%
1.5%
1000
3.7%
3.7%
3.7%
3.6%
3.4%
3.2%
3.0%
2.7%
2.2%
1.6%
750
4.3%
4.3%
4.2%
4.1%
3.9%
3.7%
3.4%
3.1%
2.6%
1.9%
500
5.3%
5.2%
5.2%
5.0%
4.8%
4.6%
4.2%
3.8%
3.2%
2.3%
400
5.9%
5.9%
5.8%
5.6%
5.4%
5.1%
4.7%
4.2%
3.5%
2.6%
300
6.8%
6.8%
6.7%
6.5%
6.2%
5.9%
5.4%
4.9%
4.1%
3.0%
200
8.3%
8.3%
8.2%
8.0%
7.6%
7.2%
6.7%
6.0%
5.0%
3.6%
150
9.6%
9.6%
9.4%
9.2%
8.8%
8.3%
7.7%
6.9%
5.8%
4.2%
100
11.8%
11.7%
11.5%
11.2%
10.8%
10.2%
9.4%
8.4%
7.1%
5.1%
50
16.7%
16.6%
16.3%
15.9%
15.3%
14.4%
13.3%
11.9%
10.0%
7.3%
23
7.4 Testing for Statistical Differences
Sampling error is also used to determine whether two population subgroups (or domains) are
significantly different with respect to a certain statistic, that is, the difference in the sampled subgroup
estimates is large enough that it would be unlikely to randomly occur if the statistics were the same
for the subgroups. Consider the hypothesis test for comparing two domains:
H0: Y1 = Y2 or Y1 – Y2 = 0
H1: Y1 ≠ Y2 or Y1 – Y2 ≠ 0
One method to test whether Y1 is different from Y2 is to calculate a confidence interval around the
difference in the sample estimates,3
. If the interval does not
⁄
contain 0, we conclude that Y1 is different from Y2 –the observed difference in the sample estimates is
not likely to randomly occur if Y1 was equal to Y2, therefore there is evidence to indicate a difference
in the population statistics. If the interval does not contain 0, we cannot conclude that Y1 is different
from Y2 – there is insufficient evidence to indicate a difference in the population statistics.
, represents the sum of the variances for two population subgroups.
The subgroup variances are estimated as described above. Table 7.3 includes the estimated 95-percent
error margins for the differences between subgroups of various size. If the observed difference is less
than or equal to the error margin, the difference is not statistically significant at the α = 0.05
significance level. If it is greater than the error margin, the difference is statistically significant at the
α = 0.05 significance level.
3
This method should only be used for large sample sizes. One rule of thumb is n1 and n2 both greater than 30.
24
Table 7.3. Estimated 95% Error Margins For the Difference Between Two Subgroups
DEFF
n1
P
1.45
7500
50,50
n2 =7500
1.9%
5000
2.2%
4000
2.3%
3000
2.5%
2000
3.0%
1500
3.3%
1000
4.0%
500
5.4%
400
6.0%
300
6.9%
200
8.4%
100
11.9%
50
16.7%
40,60
1.9%
2.1%
2.3%
2.5%
2.9%
3.3%
3.9%
5.3%
5.9%
6.8%
8.3%
11.6%
16.4%
30,70
1.8%
2.0%
2.1%
2.3%
2.7%
3.1%
3.6%
5.0%
5.5%
6.4%
7.7%
10.9%
15.3%
20,80
1.5%
1.7%
1.8%
2.0%
2.4%
2.7%
3.2%
4.4%
4.8%
5.6%
6.8%
9.5%
13.4%
10,90
1.2%
1.3%
1.4%
1.5%
1.8%
2.0%
2.4%
3.3%
3.6%
4.2%
5.1%
7.1%
10.0%
50,50
2.2%
2.4%
2.5%
2.7%
3.1%
3.5%
4.1%
5.5%
6.1%
7.0%
8.5%
11.9%
16.8%
40,60
2.1%
2.3%
2.4%
2.7%
3.1%
3.4%
4.0%
5.4%
6.0%
6.9%
8.3%
11.7%
16.4%
30,70
2.0%
2.2%
2.3%
2.5%
2.9%
3.2%
3.7%
5.1%
5.6%
6.4%
7.8%
10.9%
15.4%
20,80
1.7%
1.9%
2.0%
2.2%
2.5%
2.8%
3.3%
4.4%
4.9%
5.6%
6.8%
9.5%
13.4%
10,90
1.3%
1.4%
1.5%
1.6%
1.9%
2.1%
2.4%
3.3%
3.7%
4.2%
5.1%
7.1%
10.1%
50,50
2.3%
2.5%
2.6%
2.8%
3.2%
3.6%
4.2%
5.6%
6.2%
7.1%
8.5%
11.9%
16.8%
40,60
2.3%
2.4%
2.6%
2.8%
3.2%
3.5%
4.1%
5.5%
6.1%
6.9%
8.4%
11.7%
16.4%
30,70
2.1%
2.3%
2.4%
2.6%
3.0%
3.3%
3.8%
5.1%
5.7%
6.5%
7.8%
10.9%
15.4%
20,80
1.8%
2.0%
2.1%
2.3%
2.6%
2.9%
3.3%
4.5%
4.9%
5.6%
6.8%
9.5%
13.4%
10,90
1.4%
1.5%
1.6%
1.7%
1.9%
2.1%
2.5%
3.4%
3.7%
4.2%
5.1%
7.2%
10.1%
50,50
2.5%
2.7%
2.8%
3.0%
3.4%
3.7%
4.3%
5.7%
6.3%
7.1%
8.6%
12.0%
16.8%
40,60
2.5%
2.7%
2.8%
3.0%
3.3%
3.7%
4.2%
5.6%
6.1%
7.0%
8.4%
11.7%
16.5%
30,70
2.3%
2.5%
2.6%
2.8%
3.1%
3.4%
3.9%
5.2%
5.7%
6.5%
7.9%
11.0%
15.4%
20,80
2.0%
2.2%
2.3%
2.4%
2.7%
3.0%
3.4%
4.6%
5.0%
5.7%
6.9%
9.6%
13.4%
10,90
1.5%
1.6%
1.7%
1.8%
2.0%
2.2%
2.6%
3.4%
3.8%
4.3%
5.2%
7.2%
10.1%
50,50
3.0%
3.1%
3.2%
3.4%
3.7%
4.0%
4.6%
5.9%
6.5%
7.3%
8.7%
12.1%
16.9%
40,60
2.9%
3.1%
3.2%
3.3%
3.7%
3.9%
4.5%
5.8%
6.3%
7.1%
8.6%
11.8%
16.5%
30,70
2.7%
2.9%
3.0%
3.1%
3.4%
3.7%
4.2%
5.4%
5.9%
6.7%
8.0%
11.1%
15.5%
20,80
2.4%
2.5%
2.6%
2.7%
3.0%
3.2%
3.7%
4.7%
5.2%
5.8%
7.0%
9.7%
13.5%
10,90
1.8%
1.9%
1.9%
2.0%
2.2%
2.4%
2.7%
3.5%
3.9%
4.4%
5.2%
7.2%
10.1%
50,50
3.3%
3.5%
3.6%
3.7%
4.0%
4.3%
4.8%
6.1%
6.6%
7.5%
8.9%
12.2%
16.9%
40,60
3.3%
3.4%
3.5%
3.7%
3.9%
4.2%
4.7%
6.0%
6.5%
7.3%
8.7%
11.9%
16.6%
30,70
3.1%
3.2%
3.3%
3.4%
3.7%
3.9%
4.4%
5.6%
6.1%
6.8%
8.1%
11.2%
15.5%
20,80
2.7%
2.8%
2.9%
3.0%
3.2%
3.4%
3.8%
4.9%
5.3%
6.0%
7.1%
9.7%
13.6%
10,90
2.0%
2.1%
2.1%
2.2%
2.4%
2.6%
2.9%
3.7%
4.0%
4.5%
5.3%
7.3%
10.2%
5000
4000
3000
2000
1500
25
Table 7.3. Estimated 95% Error Margins For the Difference Between Two Subgroups (Continued)
DEFF
n1
P
1.45
1000
50,50
n2 =7500
4.0%
5000
4.1%
4000
4.2%
3000
4.3%
2000
4.6%
1500
4.8%
1000
5.3%
500
6.5%
400
7.0%
300
7.8%
200
9.1%
100
12.4%
50
17.1%
40,60
3.9%
4.0%
4.1%
4.2%
4.5%
4.7%
5.2%
6.3%
6.8%
7.6%
8.9%
12.1%
16.7%
30,70
3.6%
3.7%
3.8%
3.9%
4.2%
4.4%
4.8%
5.9%
6.4%
7.1%
8.4%
11.3%
15.7%
20,80
3.2%
3.3%
3.3%
3.4%
3.7%
3.8%
4.2%
5.2%
5.6%
6.2%
7.3%
9.9%
13.7%
10,90
2.4%
2.4%
2.5%
2.6%
2.7%
2.9%
3.2%
3.9%
4.2%
4.7%
5.5%
7.4%
10.2%
50,50
5.4%
5.5%
5.6%
5.7%
5.9%
6.1%
6.5%
7.5%
7.9%
8.6%
9.9%
12.9%
17.5%
40,60
5.3%
5.4%
5.5%
5.6%
5.8%
6.0%
6.3%
7.3%
7.7%
8.4%
9.7%
12.7%
17.1%
30,70
5.0%
5.1%
5.1%
5.2%
5.4%
5.6%
5.9%
6.8%
7.2%
7.9%
9.0%
11.8%
16.0%
20,80
4.4%
4.4%
4.5%
4.6%
4.7%
4.9%
5.2%
6.0%
6.3%
6.9%
7.9%
10.3%
14.0%
10,90
3.3%
3.3%
3.4%
3.4%
3.5%
3.7%
3.9%
4.5%
4.7%
5.2%
5.9%
7.7%
10.5%
50,50
6.0%
6.1%
6.2%
6.3%
6.5%
6.6%
7.0%
7.9%
8.3%
9.0%
10.2%
13.2%
17.7%
40,60
5.9%
6.0%
6.1%
6.1%
6.3%
6.5%
6.8%
7.7%
8.2%
8.8%
10.0%
12.9%
17.3%
30,70
5.5%
5.6%
5.7%
5.7%
5.9%
6.1%
6.4%
7.2%
7.6%
8.3%
9.4%
12.1%
16.2%
20,80
4.8%
4.9%
4.9%
5.0%
5.2%
5.3%
5.6%
6.3%
6.7%
7.2%
8.2%
10.5%
14.1%
10,90
3.6%
3.7%
3.7%
3.8%
3.9%
4.0%
4.2%
4.7%
5.0%
5.4%
6.1%
7.9%
10.6%
50,50
6.9%
7.0%
7.1%
7.1%
7.3%
7.5%
7.8%
8.6%
9.0%
9.6%
10.8%
13.6%
18.0%
40,60
6.8%
6.9%
6.9%
7.0%
7.1%
7.3%
7.6%
8.4%
8.8%
9.4%
10.5%
13.3%
17.6%
30,70
6.4%
6.4%
6.5%
6.5%
6.7%
6.8%
7.1%
7.9%
8.3%
8.8%
9.9%
12.5%
16.5%
20,80
5.6%
5.6%
5.6%
5.7%
5.8%
6.0%
6.2%
6.9%
7.2%
7.7%
8.6%
10.9%
14.4%
10,90
4.2%
4.2%
4.2%
4.3%
4.4%
4.5%
4.7%
5.2%
5.4%
5.8%
6.5%
8.2%
10.8%
50,50
8.4%
8.5%
8.5%
8.6%
8.7%
8.9%
9.1%
9.9%
10.2%
10.8%
11.8%
14.4%
18.6%
40,60
8.3%
8.3%
8.4%
8.4%
8.6%
8.7%
8.9%
9.7%
10.0%
10.5%
11.5%
14.1%
18.3%
30,70
7.7%
7.8%
7.8%
7.9%
8.0%
8.1%
8.4%
9.0%
9.4%
9.9%
10.8%
13.2%
17.1%
20,80
6.8%
6.8%
6.8%
6.9%
7.0%
7.1%
7.3%
7.9%
8.2%
8.6%
9.4%
11.5%
14.9%
500
400
300
200
100
10,90
5.1%
5.1%
5.1%
5.2%
5.2%
5.3%
5.5%
5.9%
6.1%
6.5%
7.1%
8.7%
11.2%
50,50
11.9%
11.9%
11.9%
12.0%
12.1%
12.2%
12.4%
12.9%
13.2%
13.6%
14.4%
16.7%
20.4%
40,60
11.6%
11.7%
11.7%
11.7%
11.8%
11.9%
12.1%
12.7%
12.9%
13.3%
14.1%
16.3%
20.0%
30,70
10.9%
10.9%
10.9%
11.0%
11.1%
11.2%
11.3%
11.8%
12.1%
12.5%
13.2%
15.3%
18.7%
20,80
9.5%
9.5%
9.5%
9.6%
9.7%
9.7%
9.9%
10.3%
10.5%
10.9%
11.5%
13.3%
16.3%
10,90
7.1%
7.1%
7.2%
7.2%
7.2%
7.3%
7.4%
7.7%
7.9%
8.2%
8.7%
10.0%
12.2%
26
Table 7.3. Estimated 95% Error Margins For the Difference Between Two Subgroups (Continued)
DEFF
n1
P
1.45
50
50,50
n2 =7500
16.7%
5000
16.8%
4000
16.8%
3000
16.8%
2000
16.9%
1500
16.9%
1000
17.1%
500
17.5%
400
17.7%
300
18.0%
200
18.6%
100
20.4%
50
23.6%
40,60
16.4%
16.4%
16.4%
16.5%
16.5%
16.6%
16.7%
17.1%
17.3%
17.6%
18.3%
20.0%
23.1%
30,70
15.3%
15.4%
15.4%
15.4%
15.5%
15.5%
15.7%
16.0%
16.2%
16.5%
17.1%
18.7%
21.6%
20,80
13.4%
13.4%
13.4%
13.4%
13.5%
13.6%
13.7%
14.0%
14.1%
14.4%
14.9%
16.3%
18.9%
10,90
10.0%
10.1%
10.1%
10.1%
10.1%
10.2%
10.2%
10.5%
10.6%
10.8%
11.2%
12.2%
14.1%
27
8. Nonresponse Bias Analysis
Survey nonresponse bias occurs when the propensity to respond to the survey is correlated with the
questions being asked of the respondent. However, the direct effects of nonresponse are difficult to
quantify since survey data is only available for the respondents. Therefore, we use other data sources,
such as information on the sampling frame and/or benchmark data, to evaluate nonresponse.
Generally for RDD samples, like the one used for the 2012 National Survey of Bicyclist and
Pedestrian Attitudes and Behavior, the sampling frame provides little information about the
nonrespondents other than the geo-demographic data associated with their telephone number. This
allows us to identify areas, and the characteristics of those areas, where nonresponse is highest.
However, it doesn’t tell us the characteristics of those who ultimately responded or did not respond to
the survey. Benchmark data, generally based on known socio-demographic population data, is used
to compare the sample to the population. When a sample distribution is different from the benchmark
for a particular characteristic, we infer that the effect is due to nonresponse, assuming complete
coverage of the population and an unbiased sample. Weighting survey data mitigates the risk of
nonresponse bias to the extent that the weighting variables are correlated with nonresponse propensity
and the survey items.
A Non-Response Follow-Up (NRFU) Study was conducted among respondents who had been
classified as non-contacts or refusals during the main data collection effort. The survey instrument
was 5 minutes in length and contained a few substantive questions from the main questionnaire as
well as demographic items. A total of 224 respondents completed the NRFU questionnaire, however
the results did not differ significantly from the main survey administration and were therefore
excluded from the non-response bias analysis. Any adjustment for non-response bias was based
solely on benchmark data.
Below are the sample percentages and population benchmarks for selected demographics. The
sample percentages are calculated with weights that adjust for the sampling design (including the
dual-frame adjustment) to best isolate nonresponse. The sample underrepresents the younger age
groups, adults with a high school degree or lower, and minorities. These population distributions,
taken from the 2011 American Community Survey, were used in the weighting.
Table 8.1 Sample and Population Comparison
Total
n
Total
7509
NHTSA Region
1
408
2
1155
3
812
4
1029
5
1263
6
800
7
410
8
299
9
926
10
407
Male
Pop.
(%)*
100
Sample
(%)
100
4.8
13.4
10.1
14.5
16.7
12.2
5.3
4.0
14.5
4.5
5.3
14.7
10.3
14.1
16.9
10.9
5.8
3.9
12.6
5.5
Female
n
3755
Pop.
(%)*
48.7
Sample
(%)
50.2
219
561
401
520
624
408
211
133
477
201
2.3
6.4
4.9
7.0
8.1
5.9
2.6
2.0
7.2
2.2
2.8
7.3
5.1
7.2
8.4
5.6
2.9
1.7
6.5
2.6
28
n
3754
Pop.
(%)*
51.3
Sample
(%)
49.8
189
594
411
509
639
392
199
166
449
206
2.5
7.0
5.2
7.5
8.6
6.2
2.7
2.0
7.3
2.3
2.6
7.5
5.1
6.9
8.5
5.3
2.9
2.1
6.0
2.9
Total
Male
Female
n
Pop.
(%)*
Sample
(%)
n
Pop.
(%)*
Sample
(%)
n
Pop.
(%)*
Sample
(%)
7509
100
100
3755
48.7
50.2
3754
51.3
49.8
795
1023
1160
1405
1460
1002
664
16.1
16.9
16.6
18.1
15.5
9.1
7.7
11.8
14.2
15.1
20.9
19.4
12.0
6.6
417
517
590
706
697
491
337
8.3
8.5
8.3
8.9
7.5
4.3
3.0
6.1
7.2
7.7
10.6
9.3
5.9
3.3
378
506
570
699
763
511
327
7.9
8.4
8.3
9.2
8.0
4.9
4.7
5.7
7.0
7.4
10.2
10.1
6.1
3.3
787
14.8
542
NH white
5
66.1
NH black
722
11.7
NH Asian
575
7.5
Educational Attainment by age
11.7
408
7.5
6.0
379
7.3
5.7
71.0
9.6
7.8
2692
359
296
32.2
5.4
3.6
35.1
5.0
4.0
2733
363
279
33.9
6.2
4.0
35.9
4.5
3.7
16-24
25-34
11.8
1.0
2.9
417
31
112
8.3
1.2
2.4
6.1
0.5
1.5
378
31
116
7.9
0.9
1.7
5.7
0.5
1.5
Total
Age group
16-24
25-34
35-44
45-54
55-64
64-74
75+
Race/Ethnicity
Hispanic
795
62
228
16.1
2.0
4.1
LT HS
HS grad
Some
college
273
5.4
3.8
135
2.6
1.9
138
2.8
1.9
Colleg grad
460
5.3
6.4
239
2.3
3.4
221
3.0
3.1
35-44 LT HS
69
2.1
1.1
40
1.2
0.6
29
0.9
0.5
HS grad
209
4.2
2.9
99
2.3
1.4
110
1.9
1.5
Some
college
318
5.0
4.2
171
2.3
2.3
147
2.7
2.0
Colleg grad
564
5.3
6.8
280
2.4
3.4
284
2.8
3.5
45-64 LT HS
191
4.1
2.9
101
2.1
1.6
90
2.0
1.4
HS grad
699
9.8
10.0
337
4.8
4.9
362
4.9
5.0
Some
college
771 10.1
10.8
370
4.6
5.4
401
5.5
5.5
Colleg grad
1204
9.6
16.6
595
4.8
8.1
609
4.8
8.5
65+
LT HS
177
3.6
1.9
88
1.5
1.0
89
2.1
1.0
HS grad
467
5.7
5.3
229
2.1
2.6
238
3.6
2.7
Some
college
442
3.8
4.9
210
1.6
2.3
232
2.2
2.5
Colleg grad
580
3.7
6.6
301
2.1
3.3
279
1.7
3.2
*Population Estimates were taken from the 2011 American Community Survey, conducted by the US
Census Bureau
29
Appendix A
Sample Dispositions
Figure A.1 Disposition Report for Landline Cross-section Sample
Estimated Estimated
Original
Qualified
Response
Count Household* Eligible^
88,655
T1
TOTAL
A
A1
A2
A3
A4
NON-Usable Numbers
NIS/DIS/Change#/Intercepts
Non-residential #
Computer/Fax tone
Line problem
63,740
4,559
54,727
3,163
1,291
T2
B
B1
B2
B3
Total Usable Numbers
UNKNOWN ELIGIBLE HOUSEHOLD*^
Probable unassigned number
No answer/Busy
Answering machine
24,915
9,664
3,814
2,521
3,329
C
C1
C2
C3
NOT ELIGIBLE RESPONDENT^
Language barrier
Health/Deaf
Respondent away for duration
D
D1
D2
D3
UNKNOWN ELIGIBLE RESPONDENT^
Callback
Spanish Callback not screened
Refusals not screened
E
E1
E2
E3
E4
CONTACTS SCREENED
Qualified callback
Refusals – Qualified
Terminates
Screen-outs
F
COMPLETE
A'
ESTIMATED ELIGIBLE HH RATE =T2/T1
932
261
561
110
ELIGIBLE RESPONSE RATE = E+FB' E4/(E+F)
C' SUM RESPONSE ELIGIBLE COUNT
D' RESPONSE RATE = F/C'
*Estimated Qualified HH=Original Count * A'
^Response Eligible = Qualified Household Count
* B'
A-1
8,878
5,580
28
3,270
2,716
2,688
932
923
8,788
938
340
543
0
55
340
543
0
4,503
4,503
28.10%
98.99%
25.32%
17,785
Figure A.2 Disposition Report for Cell Phone Sample
Estimated Estimated
Qualified
Response
Original
Count Household* Eligible^
46,998
T1
TOTAL
A
A1
A2
A3
A4
NON-Usable Numbers
NIS/DIS/Change#/Intercepts
Non-residential #
Computer/Fax tone
Line problem
17,653
15,445
1,402
95
711
T2
B
B1
B2
B3
Total Usable Numbers
UNKNOWN ELIGIBLE HOUSEHOLD*^
Probable unassigned number
No answer/Busy
Answering machine
29,345
11,013
25
1,603
9,385
C
C1
C2
C3
NOT ELIGIBLE RESPONDENT^
Language barrier
Health/Deaf
Respondent away for duration
D
D1
D2
D3
UNKNOWN ELIGIBLE RESPONDENT^
Callback
Spanish Callback not screened
Refusals not screened
E
E1
E2
E3
E4
CONTACTS SCREENED
Qualified callback
Refusals – Qualified
Terminates
Screen-outs
2,315
330
335
0
1,650
330
335
0
F
COMPLETE
2,212
2,212
A'
ESTIMATED ELIGIBLE HH RATE =T2/T1
474
218
187
69
ELIGIBLE RESPONSE RATE = E+FB' E4/(E+F)
C' SUM RESPONSE ELIGIBLE COUNT
D' RESPONSE RATE = F/C'
*Estimated Qualified HH=Original Count * A'
^Response Eligible = Qualified Household Count
* B'
A-2
13,332
8,655
60
4,617
6,876
4,370
474
301
8,473
62.44%
63.55%
13.81%
16,021
Figure A.3 Disposition Report for Landline Oversample
Estimated Estimated
Qualified
Response
Original
Count Household* Eligible^
57,386
T1
TOTAL
A
A1
A2
A3
A4
NON-Usable Numbers
NIS/DIS/Change#/Intercepts
Non-residential #
Computer/Fax tone
Line problem
40,460
34,925
2,826
2,112
597
T2
B
B1
B2
B3
Total Usable Numbers
UNKNOWN ELIGIBLE HOUSEHOLD*^
Probable unassigned number
No answer/Busy
Answering machine
16,926
6,550
1,652
2,528
2,370
C
C1
C2
C3
NOT ELIGIBLE RESPONDENT^
Language barrier
Health/Deaf
Respondent away for duration
D
D1
D2
D3
UNKNOWN ELIGIBLE RESPONDENT^
Callback
Spanish Callback not screened
Refusals not screened
5,448
3,810
107
1,531
E
E1
E2
E3
E4
CONTACTS SCREENED
Qualified callback
Refusals – Qualified
Terminates
Screen-outs
3,693
259
206
0
3,228
259
206
0
F
COMPLETE
794
794
A'
ESTIMATED ELIGIBLE HH RATE =T2/T1
441
164
206
71
ELIGIBLE RESPONSE RATE = E+FB' E4/(E+F)
C' SUM RESPONSE ELIGIBLE COUNT
D' RESPONSE RATE = F/C'
*Estimated Qualified HH=Original Count * A'
^Response Eligible = Qualified Household Count
* B'
A-3
1,932
542
441
124
1,529
29.49%
28.06%
22.99%
3,453
Appendix B
Survey Instrument
NHTSA Form 1148
OMB No. 2127-0684
Expiration Date:
NHTSA National Survey of Pedestrian and Bicyclist Attitudes and Behavior
Questionnaire
September 25, 2012
QLAN. WHICH LANGUAGE IS THE INTERVIEW CONDUCTED IN
1 English
2 Spanish
4548C: CELL SAMPLE
SC1. Hello, I am _____ calling on behalf of the U.S. Department of
Transportation. We are conducting a national study about personal
transportation.
Are you currently driving?
1 Yes
2 No
9 Refused
SC1a.
1
2
3
4
9
THANK AND END
THANK AND END
Are you in a safe place to talk right now?
Yes
No, call me later
THANK AND END
No, CB on land-line
RECORD NUMBER
Cell phone for business only
THANK AND END - BUSINESS#
Refused
THANK AND END –
SC2. I know I’m calling you on your cell phone, but we are conducting a
brief survey about personal transportation and we would like to send
you $10 if you are eligible and willing to answer some questions.
The survey is completely voluntary and will only take about 20
minutes. Any answers you give are kept strictly private.
[IF NECESSARY READ:
Please note that an agency may not conduct or
sponsor, and a person is not required to respond to, a collection of
information unless it displays a current valid OMB Control Number.
The OMB Control Number for this information collection is 2127-0684.
If you would like to learn more about the survey, you can call our
toll-free number at 1-866-780-8528 x5432 or visit the DOT website at
www.nhtsa.gov/pedbikesurvey.]
B-1
Are you 16 years old or older?
1
2
3
9
Yes
Yes, no time
No
Refused
SCHEDULE CALLBACK
SCREEN OUT
THANK AND END -
Qualified Level 1
SC3.
Not counting this cell phone, do you also have a regular landline phone at home?
1 Cell is only phone
SKIP TO SA3
2 Has regular landline phone at home
9 Don’t know/Refused
THANK AND END
SC4a. Of all the telephone calls that you or your family receives, are .
. . (Read List)
1 All or almost all calls received on cell phones
2 Some received on cell phones and some on regular phones (SCRN OUT:
NOT CELL MOSTLY) SKIP TO SCR1
3 Very few or none on cell phones (SCRN OUT: NOT CELL MOSTLY) SKIP
TO SCR1
8 (VOL) Don’t know (SCRN OUT: NOT CELL MOSTLY) SKIP TO SCR1
9 (VOL) Refused (SCRN OUT: NOT CELL MOSTLY) SKIP TO SCR1
SC4b. Thinking about just your LAND LINE home phone, NOT your cell
phone, if that
telephone rang when someone was home, under normal circumstances,
how likely is it that the phone would be answered? Would you say
it is … (Read List)
1
2
3
4
5
8
9
Very likely the land line phone would be answered,
Somewhat likely,
Somewhat unlikely,
Very Unlikely, or
Not at all likely the land line phone would be answered
(VOL) Don’t know
(VOL) Refused
SKIP TO SA3
B-2
4548L: LAND LINE SAMPLE
SLL1.
Hello, I am _____ calling on behalf of the U.S. Department of
Transportation. We are conducting a national study about personal
transportation.
Just to confirm, have I reached you on a landline or a cell phone?
Landline phone
SKIP TO SL1
Cell phone
(VOL) Voice Over IP (VOIP) or internet SKIP TO SL1
Refused
1
2
3
9
SLL2.
Are you currently driving?
1 Yes
2 No
9 Refused
SLL3.
1
2
3
4
9
THANK AND END
THANK AND END
Are you in a safe place to talk right now?
Yes
No, call me later
THANK AND END
No, CB on land-line
RECORD NUMBER
Cell phone for business only
THANK AND END - BUSINESS#
Refused
THANK AND END
SL1. As I mentioned I am _____ calling on behalf of the U.S. Department
of Transportation. We are conducting a national study about
personal transportation.
This collection of information is
VOLUNTARY and will be used for statistical purposes only. The
interview will take approximately 20 minutes. Your participation is
anonymous and we will not collect any personal information that
would allow anyone to identify you.
[IF NECESSARY READ: Please note that an agency may not conduct or
sponsor, and a person is not required to respond to, a collection
of information unless it displays a current valid OMB Control
Number. The OMB Control Number for this information collection is
2127-0684. If you would like to learn more about the survey, you
can call our toll-free number at 1-866-780-8528 x5432 or visit the
DOT website at www.nhtsa.gov/pedbikesurvey.]
B-3
How many persons, age 16 and older, live in this household?
[ENTER NUMBER 1-10]
97 NONE
SCREEN OUT
99 Don’t know/Refused THANK AND END
Qualified Level 1
ASK IF SL1=1.
SL1b.
May I speak with that person?
1
2
3
9
Rspn on line
Rspn called to phone
Rspn unavailable
Refused
SKIP TO SA3
GO TO SL1d
SCHEDULE CALLBACK
THANK AND END
ASK IF SL1>1
SL1c.
In order to select just one person to interview, may I please
speak to the person in your household, age 16 or older, who (has
had the most recent/will have the next) birthday?
1
2
3
9
Rspn on line
Rspn called to phone
Rspn unavailable
Refused
GO TO SA3
SCHEDULE CALLBACK
THANK AND END
SL1d.
Hello, I am _____ calling on behalf of the U.S. Department of
Transportation. We are conducting a national study about personal
transportation.
This collection of information is VOLUNTARY and
will be used for statistical purposes only. The interview will take
approximately 20 minutes. Your participation is anonymous and we
will not collect any personal information that would allow anyone
to identify you.
[IF NECESSARY READ: Please note that an agency may not conduct or
sponsor, and a person is not required to respond to, a collection
of information unless it displays a current valid OMB Control
Number. The OMB Control Number for this information collection is
2127-0684. If you would like to learn more about the survey, you
can call our toll-free number at 1-866-780-8528 x5432 or visit the
DOT website at www.nhtsa.gov/pedbikesurvey.]
Could I please confirm that you are a household member age 16 or
older?
1 Yes
2 No
9 Refused
SCHEDULE CALLBACK
THANK AND END
B-4
SKIP TO SA3
5432O: LANDLINE OVERSAMPLE
SOL1.
Hello, I am _____ calling on behalf of the U.S. Department of
Transportation. We are conducting a national study about personal
transportation.
Just to confirm, have I reached you on a landline or a cell phone?
Landline phone
SKIP TO SO1
Cell phone
(VOL) Voice Over IP (VOIP) or internet
SKIP TO SO1
Refused
1
2
3
9
SOL2.
Are you currently driving?
1 Yes
2 No
9 Refused
SOL3.
1
2
3
4
9
THANK AND END
THANK AND END
Are you in a safe place to talk right now?
Yes
No, call me later
THANK AND END
No, CB on land-line
RECORD NUMBER
Cell phone for business only
THANK AND END - BUSINESS#
Refused
THANK AND END –
SO1. As I mentioned earlier, I am _____ calling on behalf of the U.S.
Department of Transportation. We are conducting a national study
about personal transportation.
This collection of information is
VOLUNTARY and will be used for statistical purposes only. The
interview will take approximately 20 minutes. Your participation is
anonymous and we will not collect any personal information that
would allow anyone to identify you.
[IF NEEDED: Please note that an agency may not conduct or sponsor,
and a person is not required to respond to, a collection of
information unless it displays a current valid OMB Control Number.
The OMB Control Number for this information collection is 21270684.
If you would like to learn more about the survey, you can
call our toll-free number at 1-866-780-8528 X5432 or visit the DOT
website at www.nhtsa.gov/pedbikesurvey.]
B-5
How many persons, age 16 to 39, live in this household?
[ENTER NUMBER 1-10]
97 NONE
99 Don’t know/Refused
SCREEN OUT
THANK AND END
Qualified Level 1
ASK IF SO1=1.
SO1b.
May I speak with that person?
1 Rspn on line
SKIP TO SA3
2 Rspn called to phone
GO TO SO1d
3 Rspn unavailable
SCHEDULE CALLBACK
9 Refused
THANK AND END
ASK IF SO1>1
SO1c.
In order to select just one person to interview, may I please
speak to the person in your household, age 16 to 39, who (has had
the most recent/will have the next) birthday?
1
2
3
9
Rspn on line
Rspn called to phone
Rspn unavailable
Refused
GO TO SA3
SCHEDULE CALLBACK
THANK AND END
SO1d.
Hello, I am _____ calling on behalf of the U.S. Department of
Transportation. We are conducting a national study about personal
transportation.
This collection of information is VOLUNTARY and
will be used for statistical purposes only. The interview will take
approximately 20 minutes. Your participation is anonymous and we
will not collect any personal information that would allow anyone
to identify you.
[IF NEEDED: If you would like to learn more about the survey, you
can call our toll-free number at 1-866-780-8528 X 5432 or visit the
DOT website at www.nhtsa.gov/pedbikesurvey. Please note that an agency
may not conduct or sponsor, and a person is not required to respond
to, a collection of information unless it displays a current valid
OMB Control Number. The OMB Control Number for this information
collection is 2127-0684.]
Could I please confirm that you are a household member age 16 to
39?
1 Yes
2 No
9 Refused
SCHEDULE CALLBACK
THANK AND END
B-6
SA3.
Record gender from observation.
1 Male
2 Female
Qualified Level 2
B-7
(Ask only if necessary)
1
When was the last time you
stationary bikes. (READ LIST)
1
2
3
4
5
6
7
8
9
10
2
rode
a
Within the past week
Within the past month, but not the
Within the past year, but not past
1-2 years ago
3-5 years ago
More than 5 years ago
Never
Can’t ride bike/Disabled
98 (VOL) Don’t know
99 (VOL) Refused
bicycle?
not
include
past week
month
(Skip to #31)
(Skip to #31)
(Skip to #31)
(Skip to #31)
(Skip to #31)
Do you have a bicycle available for your use?
include stationary bikes.
1
Yes
2
No
8 (VOL) Don’t know
9 (VOL) Refused
Do
Again, do not
(Skip to instruction before #4)
(Skip to instruction before #4)
(Skip to instruction before #4)
If #1 = 1 or 2, skip to #4
3
Why haven’t you ridden a bicycle recently?
ended and code)
(Multiple Record) (Open
1
Bad weather
2
Too busy, no opportunity
3
Bike is broken
4
No safe place to ride
5
Disability/other health impairment
6
Other transportation is faster
7
Don’t know how to ride a bike
8
Other (specify)
98 (VOL) Don’t know
99 (VOL) Refused
Continue if #1 = 1 or 2.
4.
Otherwise skip to #20.
Thinking about the past 30 days, about how many of those days did
you ride a bicycle? (Open ended and code actual number)
00
None (Skip to #20)
B-8
0131
98
99
5
(VOL) Don’t know
(VOL) Refused
The last day you rode a bicycle, was it on a weekday or the
weekend?
1
Weekday (Monday – Friday)
2
Weekend (Saturday or Sunday)
8 (VOL) Don’t know
9 (VOL) Refused
B-9
INTERVIEWER NOTE: READ SLOWLY:)
I would now like to know about EACH of the individual trips that
you made on the last day you rode a bicycle. A TRIP is defined as
going from a starting point to a destination for a specific
purpose. If you left your house to go on a bike ride with no real
destination and returned to your house that would be ONE trip. If
you rode from your house to a friend's house for a visit, then rode
back home, that would be TWO trips. If you rode from your home to a
friend’s house, then to a store, and then back home again, that
would count as THREE trips. I am going to ask about these
individual trips one at a time.
B-10
6.
Thinking of this last day that you rode your bike, what was your
starting point for your first trip of the day? (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
11
98
99
7.
What was the main purpose of this trip? (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
98
99
8.
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Rental spot
Other (Specify)
(VOL) Don’t know
(VOL) Refused
Commuting to/from work
Commuting to/from school
Recreation
Exercise/for my health
Personal errands (to/from the store, post office, and so on)
Required for my job
Drop off/Pick up someone
Visit a friend or relative
Other (Specify)
(VOL) Don’t know
(VOL) Refused
Where did this trip end? (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
11
98
99
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Rental spot
Other (Specify)
(VOL) Don’t know/A location you cannot remember
(VOL) Refused/A location you prefer not to share
B-11
PROGRAMMER NOTE:
9.
LIMIT TO 6 TRIPS MAXIMUM
Did you take any more bike trips on this day?
1
2
8
9
Yes
No
(Skip to #14)
(VOL) Don’t know
(Skip to #14)
(VOL) Refused (Skip to #14)
(PROGRAMMER NOTE: Ask #9-#13 for each trip before going to the next trip, if applicable)
IF
Q8=98/99
OR
Q13=98/99,
READ:
appropriate) trip.” AND SKIP TO Q11.
10.
“Now,
I'll
ask
you
about
your
(read
A-E,
as
Now, I'll ask you about your (read A-E, as appropriate) trip. You
just mentioned you ended your last trip at (a) (response in #8 or
#13 A-D, as appropriate). Is this where you started your (read A-E)
trip of the day?
1
2
8
9
Yes
No
(VOL) Don’t know
(VOL) Refused
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
(For each code 1 in #10 A-E,
Autocode response from #8 or #13 A-D, as appropriate
into #11 A-E, as appropriate AND Skip to #12;
Otherwise, Continue)
B-12
11.
What was your starting point
appropriate) (DO NOT READ LIST)
for
this
trip?
1
2
3
4
5
6
7
8
9
10
11
98
99
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Rental spot
Other (Specify)
(VOL) Don’t know
(VOL) Refused
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
B-13
(Display
A-E,
as
12.
What was the main purpose of
appropriate) (DO NOT READ LIST)
1
2
3
4
5
this
trip?
(Display
6
7
8
9
98
99
Commuting to/from work
Commuting to/from school
Recreation
Exercise/for my health
Personal errands (to/from the store, post office,
and so on)
Required for my job
Drop off/Pick up someone
Visit a friend or relative
Other (specify)
(VOL) Don’t know
(VOL) Refused
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
B-14
A-E,
as
13.
Where did this trip end? (Display A-E, as appropriate) (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
11
98
99
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Rental spot
Other (Specify)
(VOL) Don’t know/A location you cannot remember
(VOL) Refused/A location you prefer not to share
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
B-15
14.
When you rode your bicycle THAT DAY, did you ride mostly on (READ
LIST)? SINGLE RECORD. READ IF NECESSARY: A bike lane refers to a
lane on the side of a road designated for bicyclists. A bike path
refers to a path, not along a roadway, which can be used by
bicyclists.
1
2
3
4
5
6
7
8
9
15.
When riding your bike in the road, did you mostly ride. . .?(READ
LIST)
1
2
3
4
8
9
16.
Facing traffic, that is, riding against the direction of the
cars, or
With traffic, that is riding in the same direction as the cars
(VOL) Varies/Depends
(VOL) Not applicable/Never ride in the road
(VOL) Don’t know
(VOL) Refused
Was anyone else with you when you were riding your bicycle that
day, or was all of your riding done alone?
1
2
8
9
17.
Paved roads, not on shoulder
Shoulders of paved roads
Bike lanes on roads
Sidewalks
(Skip to #16)
Bike paths, walking paths or trails
(Skip to #16)
Unpaved roads (e.g., dirt, gravel, sand)
Or some other surface (Specify)
(Skip to #16)
(VOL) Don’t know
(VOL) Refused
Rode with others
Rode alone
(VOL) Don’t know
(VOL) Refused
Did you feel threatened for your personal safety at any time when
you rode your bike that day?
1
2
8
9
Yes
(Continue)
No
(Skip to #20)
(VOL) Don’t know
(Skip to #20)
(VOL) Refused (Skip to #20)
B-16
18. Did you feel threatened for your personal safety because of any of
the following? How about (read and rotate A-D, then E)?
1
2
8
9
Yes
No
(VOL) Don’t know
(VOL) Refused
A.
Motorists
B.
The potential for crime
C.
Uneven walkways or roadway surfaces
D.
Dogs or other animals
E.
Something else? (If
[MULTIPLE RESPONSE]
1
2
3
4
5
6
8
9
"Yes",
ask:)
What
else?
(Open
ended)
Too much bicycle or pedestrian traffic
Lack of room to ride
Obstacles blocking path
Not maintained
No/Nothing else
Other (Specify)
(VOL) Don’t know
(VOL) Refused
If code 1 in #18A, Continue; Otherwise, Skip to #20)
19.
What
did
motorists
do
to
make
(DO NOT READ LIST) (Multiple Record)
1
2
3
4
5
6
7
8
98
99
you
feel
Cut me off
Entered intersection without looking
Drove very close to me
Honked at me
Almost hit me/near miss
Just the presence of the motorist was threatening
Too fast
Other (Specify)
(VOL) Don’t know
(VOL) Refused
B-17
threatened?
20.
Now I’d like to find out how people learn about bicycling safety.
In the past five years, have you received any training in bicycling
safety?
1
Yes
2
No
(Skip to #22)
8 (VOL) Don’t know (Skip to #22)
9 (VOL) Refused
(Skip to #22)
21.
Who provided the training to you?
(DO NOT READ LIST)
1
Bicycle store
2
Police
3
Friends
4
Teachers/schools
5
Bicycle club
6
State/Local bike programs
7
Family
8
Other (Specify)
98 (VOL) Don’t know
99 (VOL) Refused
22.
If you wanted to learn (if #20 = 1, insert the word “more”) about
bicycling safety, where would you go or look for information?
(DO NOT READ LIST) (Multiple Record)
1
Bicycle store
2
Department of Motor Vehicles
3
Police
4
Automobile Association
5
Teachers/Schools
6
Bicycle Club
7
State/Local Bike programs
8
Book/Magazine/Video Store
9
Internet
10
Family
11
NHTSA
12
Other (Specify)
98 (VOL) Don’t know
99 (VOL) Refused
Continue if #1 = 1, 2, or 3.
B-18
Otherwise skip to #31.
23.
During the past year, how much of your biking was done when it was
dark or nearly dark outside? READ LIST. SINGLE RECORD.
1
2
3
4
5
6
8
9
Nearly all
More than half
About half
Some
Almost none
None
(VOL) Don’t know
(VOL) Refused
(If code 1-4 in #23, Continue;
Otherwise, Skip to #26)
24.
When you ride your bike after dark, do you do anything to make
yourself more visible to motorists?
1
2
3
4
25.
Yes
(Continue)
No
(Skip to #26)
(VOL) Don’t know
(Skip to #26)
(VOL) Refused (Skip to #26)
What do you do to make yourself or your bike more visible after
dark? (DO NOT READ LIST) (Multiple Record)
1
2
3
4
5
6
7
8
9
Use bike headlight
Use bike taillight
Wear fluorescent or reflective clothing/shoes
Wear other lights on self or belongings
Ensure bicycle has reflectors
Ride only in well-lit areas
Other (Specify)
(VOL) Don’t know
(VOL) Refused
B-19
26.
During the past year, how often did you use an electronic device
like a cell phone or mp3 player WHILE YOU WERE RIDING YOUR BIKE and
the bike was in motion? Did you use an electronic device during:
[READ LIST]
1
2
3
4
5
6
7
8
9
Nearly all of your bike trips
More than half of your bike trips
About half of your bike trips
Some of your bike trips
Almost none of your bike trips, or
None of your bike trips
Other (Specify)
(VOL) Don’t know
(VOL) Refused
GENERAL BICYCLE HABITS
(READ:)
27.
On average during the summer months, how often do you use a
bicycle? (Read 1-4) (If necessary, read:) Summer months are May
through September.
1
2
3
4
8
9
28.
Now I would like to know about your biking habits.
At least once a week
At least once a month, but not weekly
Less than once a month, but at least once during the summer
Never
(VOL) Don’t know
(VOL) Refused
On a typical day that you ride a bicycle, about how long do you
ride? Don’t count any stops – just the average amount of time you
travel on your bike. (Open ended and code time)
Hours:
____
97
[Volunteered:
99
(Refused)
98
(Don’t Know)
and Minutes:
____
SKIP TO Q30
It differs too much to say]
SKIP TO Q30
B-20
29.
Can you tell me if it was . . .[READ LIST]
1
2
3
4
8
9
30.
Compared to about a year ago, would you say you are now riding a
bike more often, less often or about the same amount?
1
2
3
8
9
31.
Less than 30 minutes,
30 minutes to one hour,
One to two hours, or
More than two hours?
(VOL) Don’t know
(VOL) Refused
More often
Same amount
Less often
(VOL) Don’t know
(VOL) Refused
Are bike PATHS, that is, paths away from the road on which bikes can travel,
available within a quarter mile of where you live?
1
2
3
4
Yes
No
(VOL) Don’t know
(VOL) Refused
IF Q1>3, SKIP TO Q34
B-21
32.
Do you ride on bike paths . . . ? [READ LIST]
1
2
3
4
5
8
9
Every time you ride a bike
(Skip to
Most of the time
(Skip to
Some of the time
(Skip to
Hardly ever, OR
Never
(VOL) Don’t know
(Skip to
(VOL) Refused
(Skip to #34)
#34)
#34)
#34)
#34)
IF Q31>1, SKIP TO Q34
33. What is the main reason that you choose not to use the bike paths?
(Open ended and code) (INTERVIEWER NOTE: If respondent says, ‘Don't
like them’, probe for why) DO NOT READ LIST. SINGLE RECORD.
1
2
3
4
5
8
9
34.
Not in good repair
Don't go where I need to go
Too crowded with bicycles or pedestrians
Don't feel safe
Other (Specify)
(VOL) Don’t know
(VOL) Refused
Are bike LANES, that is, marked lanes on a public road reserved for
bikes to travel, available within a quarter mile of where you live?
1
2
8
9
Yes
No
(VOL) Don’t know
(VOL) Refused
IF Q1>3, SKIP TO Instruction before Q37
35.
Do you ride in bike LANES…? [READ LIST]
1
2
3
4
5
8
9
Every time you ride a bike
(Skip to Instr before
Most of the time
(Skip to Instr before
Some of the time
(Skip to Instr before
Hardly ever, OR
Never
(VOL) Don’t know
(Skip to Instr before
(VOL) Refused
(Skip to Instr before #37)
B-22
#37)
#37)
#37)
#37)
IF Q34>1, SKIP TO Instruction before Q37
36. What is the main reason that you choose not to use the bike lanes?
(Open ended and code) (INTERVIEWER NOTE: If respondent says, ‘Don't
like them’,probe for why) DO NOT READ LIST. SINGLE RECORD.
1
2
3
4
5
8
9
37.
Not in good repair
Don't go where I need to go
Too crowded with bicycles or pedestrians
Don't feel safe
Other (Specify)
(VOL) Don’t know
(VOL) Refused
If #1 = 1, 2, or 3, continue.
If #1 = 4, skip to #38.
If #1 > 4, skip to #43.
When you are bicycling, how often do you have to change your route
because of obstacles, such as construction, heavy traffic, and
roads in poor condition? Does this happen nearly all of the time,
most, some, or almost none of the time?
(INTERVIEWER NOTE: READ IF NECESSARY: Obstacles refer to any
physical object which would cause the rider to detour off their
intended path and are not limited to the examples given above.)
1
Nearly all of the time
2
Most of the time
3
Some of the time
4
Almost none of the time
8 (VOL) Don’t Know
9 (VOL) Refused
38.
In the past two years, were you ever injured while you were riding
a bike? Only count injuries that required attention by a medical
professional.
1
2
8
9
39.
Yes
No
(Skip to instruction before #41)
(VOL) Don’t Know
(Skip to instruction before #41)
(VOL) Refused (Skip to instruction before #41)
Was this injury a result of being hit by a motor vehicle?
1
2
8
9
Yes
(Skip to instruction before #41)
No
(VOL) Don’t Know
(Skip to instruction before #41)
(VOL) Refused (Skip to instruction before #41)
B-23
40.
How did you injure yourself while riding your bike?
and code)
Specify
98
(Don’t Know)
99
(Refused)
.
If #1 > 3, skip to #43.
41.
(Open ended
Otherwise continue.
When riding a bike, do you wear a helmet for . . . ? (READ LIST)
1
2
3
4
5
6
8
9
All of your rides
Nearly all of your rides
Most of your rides
Some of your rides
Not very many of your rides
Never
(VOL) Don’t Know
(VOL) Refused
(If code 1 in #41, Skip to #43;
Otherwise, Continue)
Now, I am going to read a list of reasons people give when asked why
they do not wear a bike helmet.
42.
What are the reasons you don't always wear a bike helmet? Please
answer Yes or No after I read each one.
Is it because (read and
rotate A-I, then read J)?
1
2
8
9
Yes
No
(VOL) Don’t Know
(VOL) Refused
A.
You forget to wear it
B.
You don’t think helmets provide much protection in case of
accident
C.
You don’t like the way you look when you wear a helmet
D.
Helmets obstruct your vision
E.
Helmets are uncomfortable
B-24
F.
You don’t wear a helmet for short trips
G.
It’s too hot wearing a helmet
H.
Helmets cost too much
I.
You don’t have a helmet
J.
Some other reason? (If "Yes", ask:) What other reason? (Open
ended and code)
1
2
3
8
9
43.
Don’t
No/No
Other
(VOL)
(VOL)
need to wear one
other reason
(Specify)
Don’t Know
Refused
In your opinion, how much protection against HEAD injuries do bike
helmets provide children?
Would you say bike helmets provide
children very little protection, some protection, or a lot of
protection against head injuries?
1
2
3
8
9
Very little protection
Some protection
A lot of protection
(VOL) Don’t Know
(VOL) Refused
B-25
44.
What about for adults? Do bike helmets provide adults very
little protection, some protection, or a lot of protection against
HEAD injuries?
1
2
3
8
9
Very little protection
Some protection
A lot of protection
(VOL) Don’t Know
(VOL) Refused
IF Q1=8, SKIP TO Q47
45. How satisfied are you with how your local community is designed for
making bike riding safe? Are you . . . ? [READ LIST]
1
2
3
4
5
8
9
46.
What changes, if any, would you like to see your local government
make in your community for bicyclists? (DO NOT READ LIST) (Multiple
Record)
1
2
3
4
5
6
7
8
9
47.
Very satisfied
Somewhat satisfied
Neither satisfied nor dissatisfied
Somewhat dissatisfied
Very dissatisfied
(VOL) Don’t Know
(VOL) Refused
More bike trails
More bike paths
More bike lanes
Allow bikes on sidewalks
Don't allow bikes on sidewalks
Other (specify)
None, can’t think of any
(VOL) Don’t Know
(VOL) Refused
Is there a law or ordinance in your state, city, or county that
requires adults and/or children to wear a helmet when riding a
bike?
1
2
8
9
Yes
No
(Skip to #50)
(VOL) Don’t Know
(Skip to #50)
(VOL) Refused (Skip to #50)
B-26
48.
Is it a state, city, or county law?
MULTIPLE RECORD.
1
State law
2
City law
3
County law
4
Other (specify)
8 (VOL) Don’t Know
9 (VOL) Refused
49.
Does this law require all bicyclists, or only children, to wear
helmets?
1
2
8
9
50.
All bicyclists
Only children
(VOL) Don’t Know
(VOL) Refused
Do you favor or oppose laws that require (read and rotate A-B)?
A.
Children to wear helmets whenever they are riding a bike
B.
Adults to wear helmets whenever they are riding a bike
1
2
3
8
9
Favor
Oppose
(VOL) It depends (Specify)
(VOL) Don’t Know/No opinion
(VOL) Refused
B-27
PEDESTRIANS:
GENERAL
(READ:)
51.
This next section is about walking rather than biking. By
walking we mean any outdoor walking, jogging, or running that
lasts at least 5 minutes or more. (INTERVIEWER NOTE: If
respondent asks, they should NOT include roller-blading,
roller-skating, skateboarding and scooter use) [INTERVIEWER
NOTE: Each trip should start at the point where the respondent
was on foot (either walking, jogging or running) and end at
their next destination.
When was the last time you walked, jogged, or ran outside for 5
minutes or more? (Open ended and code time frame) [READ LIST]
1 Within the past week
(Continue)
2 Within the past month, but not the past week (Continue)
3 Within the past year, but not past month
(Skip to #68)
4 1-2 years ago
(Skip to Read before #74)
5 3-5 years ago
(Skip to Read before #74)
6 More than 5 years ago
(Skip to Read before #74)
7 (VOL) Never
(Skip to Read before #74)
8 (VOL) Cannot walk/disabled (Skip to Read before #74)
98 (VOL) Don’t Know
(Skip to Read before #74)
99 (VOL) Refused
(Skip to Read before #74)
52.
Thinking about the past 30 days, about how many of those days did
you walk, jog, or run outside? (Open ended and code actual number)
00
None
(Skip to #68)
0131
98
99
(VOL) Don’t Know
(VOL) Refused
B-28
53.
The last day you walked, jogged, or ran outside for 5 minutes or
more, was it on a weekday or the weekend?
1
Weekday (Monday – Friday)
2
Weekend (Saturday or Sunday)
8 (VOL) Don’t Know
9 (VOL) Refused
(INTERVIEWER NOTE: READ SLOWLY:)
I would now like to know about EACH of the individual trips
that you made on the last day you walked. A TRIP is defined as
going from a starting point to a destination for a specific
purpose. If you left your house on a walk with no real
destination and returned to your house that would be ONE trip.
If you walked from your house to a friend's house for a visit,
then walked back home, that would be TWO trips. If you walked
from your home to a friend’s house, then to a store, and then
back home again, that would count as THREE trips. I am going
to ask about these individual trips one at a time.
54.
What was your starting point for your first trip of the day?
(DO NOT READ LIST)
Each trip should start at the point where you were on foot, either
walking, jogging or running, and end at your next destination.
1
2
3
4
5
6
7
8
9
10
98
99
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
B-29
55.
What was the main purpose of this trip?
1
2
3
4
5
6
7
8
9
10
11
98
99
56.
Commuting to/from work
Commuting to/from school
Recreation
Exercise/for my health
Personal errands (to/from the store, post office,
and so on)
Required for my job
Drop off/Pick up someone
Visit a friend or relative
Walk the dog
Escort child to school
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
Where did this trip end? (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
98
99
57.
(DO NOT READ LIST)
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Other (Specify)
(VOL) Don’t Know/A location you cannot remember
(VOL) Refused/A location you prefer not to share
Did you take any more walking trips on this day? Again I want you
to include jogging and running trips in addition to walking trips.
1
2
8
9
Yes
No
(VOL) Don’t Know
(VOL) Refused
(Skip to #62)
(Skip to #62)
(Skip to #62)
B-30
(PROGRAMMER NOTE: Ask
applicable)
IF
Q56=98/99
OR
#57-#61
q61=98/99
for
READ:
appropriate) trip.” AND SKIP TO Q59.
58.
each
“Now,
trip
I'll
before
ask
going
you
to
about
the
your
next
trip,
if
(read
A-E,
as
Now, I'll ask you about your (read A-E, as appropriate) trip. You
just mentioned you ended your last trip at (a) (response in #56 or
#61 A-D, as appropriate). Is this where you started your (read A-E)
trip of the day?
1
2
8
9
Yes
No
(VOL) Don’t Know
(VOL) Refused
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
(For each code 1 in #58 A-E,
Autocode response from #56 or #61 A-D, as appropriate
into #59 A-E, as appropriate AND Skip to #60;
Otherwise, Continue)
B-31
59.
What was your starting point
appropriate) (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
98
99
for
this
trip?
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
B-32
(Display
A-E,
as
60.
What was the main purpose of
appropriate) (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
11
98
99
this
trip?
(Display
Commuting to/from work
Commuting to/from school
Recreation
Exercise/for my health
Personal errands (to/from the store, post office,
and so on)
Required for my job
Drop off/Pick up someone
Visit a friend or relative
Walk the dog
Escort child to school
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
B-33
A-E,
as
61.
Where did this trip end? (Display A-E, as appropriate) (Open ended and code)
1
2
3
4
5
6
7
8
9
10
98
99
Home
Friend or relative’s home
Work
School/Campus
Park/field
Grocery store/Drug store/Convenience store
Mall/Strip mall/Shopping center
Restaurant
Train/subway/bus station or stop
Other (Specify)
(VOL) Don’t Know/A location you cannot remember
(VOL) Refused/A location you prefer not to share
A.
(If First Loop, ask:) Second
B.
(If Second Loop, ask:) Third
C.
(If Third Loop, ask:) Fourth
D.
(If Fourth Loop, ask:) Fifth
E.
(If Fifth Loop, ask:) Sixth
B-34
62.
When you were walking, jogging or running THAT DAY, did you walk,
jog or run mostly on . . . ? [READ LIST]
1
2
3
4
5
6
7
8
9
63.
3
4
8
9
Facing traffic, that is, walking against traffic, or
With traffic, that is walking in the same direction as the
cars
(VOL) Varies/Depends
(VOL) Not applicable/Never walk in the road
(VOL) Don’t Know
(VOL) Refused
Was anyone else with you when you were walking, jogging, or
running, or was all your walking, jogging, or running done alone?
1
2
8
9
65.
to #64)
to #64)
to #64)
sand)
to #64)
to #64)
to #64)
When you were walking, jogging, or running (in the road/on the
shoulder), were you usually walking, jogging or running . . . ?
[READ LIST]
1
2
64.
Paved roads, not on shoulder
Shoulders of paved roads
Grass or fields
(Skip
Sidewalks
(Skip
Bike paths, walking paths or trails(Skip
Unpaved roads (for example dirt, gravel,
Or some other surface (Specify)
(Skip
(VOL) Don’t Know
(Skip
(VOL) Refused
(Skip
Walked with others
Walked alone
(VOL) Don’t Know
(VOL) Refused
Did you feel threatened for your personal safety at any time while
walking, jogging or running that day?
1
2
8
9
Yes
No
(VOL) Don’t Know
(VOL) Refused
(Skip to #68)
(Skip to #68)
(Skip to #68)
B-35
66.
Did you feel threatened for your personal safety because of any
of the following? How about (read and rotate A-D, then E)?
1
2
8
9
Yes
No
(VOL) Don’t Know
(VOL) Refused
A.
Motorists
B.
The potential for crime
C.
Uneven walkways or road surfaces
D.
Dogs or other animals
E.
Something else? (If "Yes", ask:) What else?
(DO NOT READ LIST) [MULTIPLE RESPONSE]
1
2
3
4
5
6
8
9
Too much bicycle or pedestrian traffic
Lack of room to walk or run
Obstacles blocking path
Not maintained
No/Nothing else
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
(If code 1 in #66-A, Continue;
Otherwise, Skip to #68)
67.
What did motorists do to make you feel threatened?
DO NOT READ LIST (Multiple Record)
1
2
3
4
5
6
7
8
98
99
Cut me off
Entered intersection without looking
Drove very close to me
Honked at me
Almost hit me/near miss
Just the presence of the motorist was threatening
Too fast
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
B-36
68.
During the past year, how much of your walking was done when it was
dark or nearly dark outside?
1
2
3
4
5
6
8
9
Nearly all
More than half
About half
Some
Almost none
None
(VOL) Don’t Know
(VOL) Refused
(If code 1-4 in #68, Continue;
Otherwise, Skip to #71)
69.
When you walk after dark, do you do anything to make yourself more
visible to motorists?
1
2
8
9
70.
Yes
No
(Skip to #71)
(VOL) Don’t Know
(Skip to #71)
(VOL) Refused (Skip to #71)
What do you do to make yourself more visible when walking after
dark? (DO NOT READ LIST)(Multiple Record)
1
2
3
4
5
8
9
Wear light colored clothing
Wear fluorescent or reflective clothing/Shoes
Wear or carry a flashlight
Walk only in well-lit areas
Other (list)
(VOL) Don’t Know
(VOL) Refused
B-37
71.
During the past year, how often did you use an electronic device
like a cell phone or mp3 player WHILE YOU WERE walking outside? Do
not count instances when you stopped walking. Did you use an
electronic device during: [READ LIST]
1
2
3
4
5
6
7
8
9
Nearly all of your outdoor walking trips
More than half of your walking trips
About half of your walking trips
Some of your walking trips
Almost none of your walking trips, or
None of your walking trips
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
GENERAL WALKING HABITS
(READ:)
72.
On average during the summer months, how often do you walk? (Read
1-4) (If necessary, read:) Summer months are May through September.
1
2
3
4
8
9
73.
Now I would like to know about your walking habits.
At least once a week
At least once a month, but not weekly
Less than once a month, but at least once during the summer
Never
(VOL) Don’t Know
(VOL) Refused
Compared to about a year ago, would you say you are now walking
more often, less often or about the same amount?
1
2
3
8
9
More often
Same amount
Less often
(VOL) Don’t Know
(VOL) Refused
B-38
Now I’d like you to think of the neighborhood where you live.
74.
Are there sidewalks in your neighborhood (Read 1-4):
1
Along almost all streets
2
Along most streets
3
Along some streets, or
4
Along no streets
(Skip To Instruction before Q78)
8 (VOL) Don’t Know
9 (VOL) Refused
75.
In what condition are these sidewalks?
good, fair, or poor condition?
Are they in excellent,
1
Excellent
2
Good
3
Fair
4
Poor
8 (VOL) Don’t Know
9 (VOL) Refused
If #51 = 4, skip to instruction before #78
If #51 > 4, skip to Instruction before #81
76.
Do you use sidewalks . . . ? [READ LIST]
1
2
3
4
5
6
8
9
Every time you walk, jog or run outside(Skip to instr before #78)
Most of the time
(Skip to instr before #78)
Some of the time
(Skip to instr before #78)
Hardly ever, OR
Never
(VOL) It depends if I am walking or jogging/running (Skip to
instr before #78)
(VOL) Don’t Know
(Skip to instr before #78)
(VOL) Refused
(Skip to instr before #78)
B-39
77.
What is the main reason that you hardly ever or never use
sidewalks? (DO NOT READ LIST)
(INTERVIEWER NOTE: If respondent says, Don't like them; Probe for
why)
1
2
3
4
5
6
8
9
Not in good repair
Don't go where I need to go
Too crowded
Prefer softer surface
Don't feel safe
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
IF Q51>4, SKIP TO Instruction before Q81
78.
In the past two years, were you ever injured while you were
walking? Only count injuries that required attention by a medical
professional.
1
2
8
9
79.
(Skip to instr before #81)
(Skip to instr before #81)
(Skip to instr before #81)
Was this injury a result of being hit by a motor vehicle?
1
2
8
9
80.
Yes
No
(VOL) Don’t Know
(VOL) Refused
(Skip to instr before #81)
Yes
No
(VOL) Don’t Know
(VOL) Refused
(Skip to instr before #81)
(Skip to instr before #81)
How did you injure yourself while you were walking?
(Open ended and code)
Specify
98
(Don’t Know)
99
(Refused)
.
B-40
IF Q51=8, SKIP TO Intro before Q83
81. How satisfied are you with how your local community is designed for
making walking safe? Are you . . . ? [READ LIST]
1
2
3
4
5
8
9
82.
Very satisfied
Somewhat satisfied
Neither satisfied nor dissatisfied
Somewhat dissatisfied
Very dissatisfied
(VOL) Don’t Know
(VOL) Refused
What changes, if any, would you like to see your local government
make in your community for pedestrians? (DO NOT READ LIST) (Multiple
Record)
1
2
3
4
5
6
8
9
More crosswalks
More sidewalks
More lights on streets
More lights on paths/trails
Other (Specify)
None, can’t think of any
(VOL) Don’t Know
(VOL) Refused
For the next couple of questions, please tell me what in your opinion is
correct. First,
83.
Are bicyclists supposed to stop at traffic lights and stop signs,
like motor vehicles, or are they supposed to use their own judgment
on whether they need to stop at red lights and stop signs?
1
2
8
9
Must stop, like motor vehicles
Can use own judgment
(VOL) Don’t Know
(VOL) Refused
B-41
84.
What do flashing red lights on a school bus mean for an approaching
car? Do they mean . . .
1
2
3
4
8
9
85.
Do drivers in your community usually yield to pedestrians in
crosswalks?
1
2
8
9
86.
Stop until lights stop flashing, or
Slow and then proceed with caution, or
Be prepared to stop, if necessary?
(VOL) Depends if there is a median in the road
(VOL) Don’t Know
(VOL) Refused
Yes
No
(VOL) Don’t Know
(VOL) Refused
Now I’m going to read you a few statements. Please tell me whether
you agree, disagree, or neither agree nor disagree. (read and
rotate A-E)?
1
2
3
8
9
Agree
Neither agree nor disagree
Disagree
(VOL) Don’t Know
(VOL) Refused
DO NOT ASK Q86a or Q86b if Q51=8
A.
I would like to walk more than I am currently walking
B.
I would like to bicycle more than I am currently bicycling
C.
Bicyclists are just as entitled to ride on the road as are
motorists
D.
Manuals used to study for a driver’s license should include
information about how to avoid accidents with pedestrians and
bicyclists
E.
A driver who doesn’t yield to pedestrians walking legally at a
crosswalk should be ticketed
B-42
87
(If 86-A is Agree) What would you say is the most important reason
why you do not walk as much as you would like? (DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
11
12
13
98
99
88.
(If 86-B is Agree) What would you say is the most important
reason why you do not bicycle as much as you would like?
(DO NOT READ LIST)
1
2
3
4
5
6
7
8
9
10
11
12
13
98
99
89.
Too busy
Poor health
No one to walk with
No sidewalks/sidewalks in poor condition
No shops or other interesting places to go
Fear street crime
Too many cars
Fast traffic
Have things to carry
Weather isn’t good for walking
Don’t think about it
Safety - unspecified
Other (specify)
(VOL) Don’t Know
(VOL) Refused
Too busy
Poor health
No one to bike with
No sidewalks/sidewalks in poor condition
No shops or other interesting places to go
Fear street crime
Too many cars
Fast traffic
Have things to carry
Weather isn’t good for bicycling
Don’t think about it
Safety - unspecified
Other (Specify)
(VOL) Don’t Know
(VOL) Refused
Is it safe or dangerous to walk in your neighborhood or does it
depend?
1
Safe
2
Dangerous
3
It depends
8 (VOL) Don’t Know
9 (VOL) Refused
(Skip to #91)
(Skip to #90)
(Skip to #91)
(Skip to #91)
B-43
89a.
What does it depend on?
(OPEN-END)
90.
Why do you
(OPEN-END)
feel
it’s
dangerous
(Specify)
91.
walk
in
your
neighborhood?
.
Is it safe or dangerous to ride a bicycle in your neighborhood or
does it depend?
1
Safe
2
Dangerous
3
It depends
8 (VOL) Don’t Know
9 (VOL) Refused
91a.
to
(Skip to #93)
(Skip to #92)
(Skip to #93)
(Skip to #93)
What does it depend on?
(OPEN-END)
92
Why do you feel it
neighborhood? (OPEN-END)
(Specify)
98
99
is
dangerous
.
(VOL) Don’t Know
(VOL) Refused
B-44
to
ride
a
bicycle
in
your
CHILDREN WALKING/BIKING
93.
How many children, less than 16 years of age, currently reside in
your household? Please do not count students living away from home
or boarders. (DO NOT READ LIST)
0
1
2
3
4
5
6
7
8
9
94.
None
(Skip to #98)
One
Two
Three
Four
Five
Six
Seven or more
(VOL) Don’t Know
(Skip to #98)
(VOL) Refused (Skip to #98)
In your opinion, what is the youngest age that a child is able to
cross a neighborhood street alone?
A neighborhood street is
defined as having low traffic volume and low traffic speeds.
Age
98 (VOL) Don’t Know
99 (VOL) Refused
95
How old is [the/the oldest] child residing in your household?
Age
98
99
(VOL) Don’t Know
(VOL) Refused
If #95 < 5, Skip to #98
96.
How many days does this child ride a bicycle during a typical week
in the Summer? (If necessary, read:) Summer months are May through
September.
98
99
(0-7)
(VOL) Don’t Know
(VOL) Refused
If #96 = 0, Skip to #98
B-45
97
When riding a bicycle, does this child wear a helmet for . . .
[READ LIST]
1
All rides
2
Nearly all rides
3
Most rides
4
Some rides
5
Not very many rides, or
6
Never
8
(VOL) Don’t Know
9
(VOL) Refused
(READ:)
98.
Now, I have a few questions about the area where you live.
Do you currently live in a . . . ? [READ LIST]
1
2
3
4
5
8
9
House
Townhouse or row house
Apartment, condo, or co-op
Mobile home, OR
Other (Specify)
(VOL) Don’t know
(VOL) Refused
B-46
99.
These next questions
mile around where you
about four football
appropriate) within ¼
ask about the area that is within a quarter
live. [(If necessary, read:) Or the length of
or soccer fields.] Are there (read A-I, as
mile of where you live? [ROTATE A-I]
1
2
8
9
Yes
No
(VOL) Don’t know
(VOL) Refused
A.
Single-family houses
B.
Townhouses, apartments or condos
C.
Mobile homes
D.
Parks or recreational areas
E.
Farms or ranches
F.
Commercial businesses such as stores or restaurants
G.
Public buildings
offices
H.
Industrial buildings or factories
I.
Heavy street traffic
such
as
schools,
B-47
hospitals
or
government
DEMOGRAPHICS BEGIN HERE:
(READ:)
Now, I have just
purposes only.
a
few
last
questions
for
classification
AGE:
100. What is your age? (Open ended and code actual age)
99
99+
998
999
(VOL) Don’t know
(VOL) Refused
(If DK or RF in #100 Continue;
Otherwise, Skip to #102)
AGE:
101. Please stop me when I reach the category that includes your age?
(Read 01-08)
1
2
3
4
5
6
7
8
98
99
16 or
18 to
25 to
35 to
45 to
55 to
65 to
75 or
(VOL)
(VOL)
17
24
34
44
54
64
74, or
older
Don’t know
Refused
EMPLOYMENT STATUS:
102. Are you currently employed full-time, part-time, unemployed and
looking for work, retired, going to school, a homemaker, or do you
do something else? [MULTIPLE RECORD]
1
2
3
4
5
6
7
8
98
99
Employed full-time
Employed part-time
Unemployed and looking for work
Retired
Going to school
Homemaker
(VOL) Disabled
Something else (Specify)
(VOL) Don’t know
(VOL) Refused
B-48
EDUCATION:
103. What is the highest grade or year of school you have completed?
(DO NOT READ LIST)
1
2
3
4
5
6
10
7
8
9
98
99
No formal education
First through 7th grade
8th grade
Some high school
High school graduate or GED
Some college
2-year technical/Associates degree
Four-year college graduate
Some graduate school
Graduate degree
(VOL) Don’t know
(VOL) Refused
ETHNICITY:
104. Are you of Hispanic or Latino origin or descent?
1
2
8
9
Yes
No
(VOL) Don’t know
(VOL) Refused
RACE:
105. Which of the following racial categories describes you?
select more than one. READ LIST AND MULTIPLE RECORD.
1
2
3
4
5
6
7
8
9
American Indian or Alaska Native
Asian
Black or African American
Native Hawaiian or Other Pacific Islander
White
(VOL) Hispanic/Latino
(VOL) Other (SPECIFY)
(VOL) Don’t know
(VOL) Refused
(If code 6 ONLY in #105, Continue;
Otherwise, Skip to #107)
B-49
You may
106. Do you consider yourself to be white-Hispanic or black-Hispanic?
1
2
3
4
8
9
White-Hispanic
Black-Hispanic
(VOL) Hispanic/Respondent refused to discriminate
Other (Specify)
(VOL) Don’t know
(VOL) Refused
INCOME:
107. Which of the following categories best describes your total
household income before taxes in 2011? Your best estimate is fine.
Would it be (read 1-7)?
1
2
3
4
5
6
7
8
9
109
Less than $5,000
$5,000 to less than $15,000
$15,000 to less than $30,000
$30,000 to less than $50,000
$50,000 to less than $75,000
$75,000 to less than $100,000, OR
$100,000 or more
(VOL) Don’t know
(VOL) Refused
How often do you drive a motor vehicle?
Almost every day, a few
days a week, a few days a month, a few days a year, or do you never
drive?
1
2
3
4
5
6
7
8
9
Almost every day/every day
Few days a week
Few days a month
Few days a year
Never
More than a year ago since drove
Other (Specify)
(VOL) Don’t know
(VOL) Refused
B-50
110. How many licensed motor vehicles are owned, leased, or available for
regular use by members of your household? (DO NOT READ LIST)
0
None
1
One
2
Two
3
Three
4
Four
5
Five
6
6 or more
7 (VOL) Zip car, etc
8 (VOL) Don’t know
9 (VOL) Refused
111. Do you currently have any disability, health impairment or condition
that limits the amount of walking you can do?
1
2
3
4
8
9
112
Yes, I use a wheelchair
(Skip to Q113)
Yes, I use a motorized chair (Skip to Q113)
(Skip to Q113)
Don’t know
(Skip to Q113)
Refused
(Skip to Q113)
Do you use special equipment to help you walk, or do you use a
wheelchair, or do you use a motorized chair?
1
2
3
4
8
9
113.
Yes
(VOL)
(VOL)
No
(VOL)
(VOL)
Yes, special equipment
Yes, a wheelchair
Yes, a motorized chair
No
(VOL) Don’t know
(VOL) Refused
In general, how easy or difficult is it for you to travel to the
places in your COMMUNITY where you want to go? Do not include out
of town travel. Would you say it is (Read 1-4):
1
2
3
4
5
8
9
Very easy;
Somewhat easy;
Somewhat difficult; or
Very Difficult.
(VOL) It depends on where I am traveling from
(VOL) Don’t know
(VOL) Refused
B-51
(Skip To Q116)
(Skip To Q116)
(Skip To Q116)
(Skip To Q116)
114. Where in your community do you find it more difficult to travel
from?
(DO NOT READ LIST) (Multiple Record)
RI NOTE: Probe for a specific place such as home or work, not a general
area such as a neighborhood name.
1
2
3
4
5
8
9
115.
Home
Work
Doctor’s Office
Place doesn’t matter/All the same
Other (Specify)
(VOL) Don’t know
(VOL) Refused
What are the reasons it is difficult for you to travel to the
places in your community where you want to go? (DO NOT READ LIST)
(Multiple Record)
1
2
3
4
8
9
Don’t have access to vehicle
Vehicles can’t accommodate mobility equipment
Sidewalks are inadequate/poor condition
Other (Specify)
(VOL) Don’t know
(VOL) Refused
116. May I please have your ZIP code?
ENTER 5 DIGIT ZIP CODE:
99998 (VOL) Don't Know
99999 (VOL) Refused
ASK ONLY FOR LANDLINE SAMPLE, OR IF SC3=2, ELSE SKIP TO Q119
118. And, NOT including cell phones or lines dedicated to a fax machine,
modem or used strictly for business purposes, how many different
phone NUMBERS do you have coming into your household? (DO NOT READ
LIST)
1
2
3
4
5
6
8
9
One
Two
Three
Four
Five or more
(VOL) No landline phone in home for non-business purposes
(VOL) Don’t know
(VOL) Refused
B-52
119. During the past 12 months, has your household been without
telephone service for 1 week or more? Do not include interruptions
of telephone service because of weather or natural disasters.
1 Yes
2 No
8 (VOL) Don’t know
9 (VOL) Refused
ASK ONLY FOR LANDLINE SAMPLE
120. Do you have a cell phone in addition to the line we are speaking on
right now?
1 This is only phone
2 Also has cell phone
8 (VOL) Don’t Know
9 (VOL) Refused
CELL SAMPLE ONLY:
121. Including yourself, how many persons age 16 and older live in your
household?
[ENTER NUMBER 1-10]
97 NONE
98 (VOL) Don’t know
99 (VOL) Refused
ASK ONLY IF LANDLINE SAMPLE AND (Q120=2)
122. Of all the telephone calls that you or your family receives, are .
. . (Read List)
1 All or almost all calls received on cell phones
2 Some received on cell phones and some on regular phones
3 Very few or none on cell phones
8 (VOL) Don’t know
9 (VOL) Refused
B-53
ASK ONLY IF LANDLINE SAMPLE AND (Q120=2)
123.Thinking about just your LAND LINE home phone, NOT your cell phone,
if that
telephone rang when someone was home, under normal circumstances,
how likely is it that the phone would be answered? Would you say it
is … (Read List)
1 Very likely the land line phone would be answered,
2 Somewhat likely,
3 Somewhat unlikely,
4 Very Unlikely, or
5 Not at all likely the land line phone would be answered
8 (VOL) Don’t know
9 (VOL) Refused
124. Did you visit the National Highway Traffic Safety Administration
website to find out more information about the survey? (at
www.nhtsa.dot.gov )
1
2
8
9
Yes
No
(DK)
(Refused)
FOR LANDLINE AND LANDLINE OVERSAMPLE ONLY
Those are all the questions I have for you.
participation.
Thank you for your
FOR CELL SAMPLE ONLY
C1. May I please have your name, street address, city, and state and
ZIP code so I can send you your $10 incentive check?
ENTER
ENTER
ENTER
ENTER
ENTER
NAME:
ADDRESS:
CITY:
STATE:
ZIP:
Those are all the questions I have for you. Thank you for your
participation.
SCR1. I am sorry but you are not eligible to participate in the survey
today. Thank you for your cooperation and I hope you have a pleasant
evening.
RI NOTE: IF NEEDED FOR 5432c: I am sorry but you are not eligible to
receive the $10 incentive.
(THANK RESPONDENT)
B-54
DOT HS 811 841 C
October 2013
10002c-092713-v1a
| File Type | application/pdf |
| Author | Paul Schroeder |
| File Modified | 2013-10-01 |
| File Created | 2013-09-27 |