WCCE ss new 0071607_Part B

SUPPORTING STATEMENT
WEST COAST COMMUNITY ECONOMIC DATA COLLECTION
OMB CONTROL NO.: 0648-xxxx

B. COLLECTIONS OF INFORMATION EMPLOYING STATISTICAL METHODS
1. Describe (including a numerical estimate) the potential respondent universe and any
sampling or other respondent selection method to be used. Data on the number of entities
(e.g. establishments, State and local governmental units, households, or persons) in the
universe and the corresponding sample are to be provided in tabular form. The tabulation
must also include expected response rates for the collection as a whole. If the collection has
been conducted before, provide the actual response rate achieved.
The total sample universes for businesses and households will be the total numbers of each in
each of eight representatively selected small to medium sized communities on the West Coast.
Total number of households will be determined from U.S. Census records and addresses will be
obtained from public records searches. The total number of businesses by ZIP code and by 2digit North American Industry Classification System (NAICS) will be obtained from the U.S.
Economic Census and from County Business Patterns. The sample universe of recreational
visitors is estimated from a study of visitors to Oregon ports done by the U.S. Army Corps of
Engineers (Wen-Huei Chang and R. Scott Jackson, Economic Impacts of Recreation Activities at
Oregon Coastal and River Ports, ERD/EL TR-03-12, U.S. Army Corps of Engineers, August
2003).
The potential respondent universe of households, businesses and recreational visitors is as
follows:
Zip Code - City

Population
2,811

Households Businesses Total
Payroll
Employment
1,884
105
1,180
$25,167,000

Recreational
Visitation
35,000

98595 Westport, WA
98624 - Ilwaco,
WA
97365 - Newport,
OR
97444 - Gold
Beach, OR
95531 - Crescent
City, CA
94923 - Bodega
Bay, CA
93442 - Morro
Bay, CA
92629 - Dana
Point, CA

1,337

798

64

562

$12,423,000

20,000

10,555

5,550

600

5,225

$122,420,000 64,220

4,768

2,622

189

1,204

$25,512,000

27,969

23,785

8,718

427

3,546

$81,258,000

20,000

1,769

875

58

543

$12,466,000

70,000

10,891

6,504

385

2,784

$56,417,000

65,000

27,728

12,703

802

7,781

$202,216,000 80,000

1

Data Source: Demographic data is from the 2000 Census. Business data is from the 2003
County Business Patterns. Visitation data is estimated from data taken from Wen-Huei Chang
and R. Scott Jackson, Economic Impacts of Recreation Activities at Oregon Coastal and River
Ports, ERD/EL TR-03-12, U.S. Army Corps of Engineers, August 2003.
2. Describe the procedures for the collection, including: the statistical methodology for
stratification and sample selection; the estimation procedure; the degree of accuracy
needed for the purpose described in the justification; any unusual problems requiring
specialized sampling procedures; and any use of periodic (less frequent than annual) data
collection cycles to reduce burden.
Households and business
Households and businesses will be randomly selected for inclusion in the study. Names, address,
and telephone numbers for businesses and households will be obtained from local government
records and from public record searches. The formula for calculating the sample size for a
simple random sample without replacement is as follows:
2

⎛ zσ ⎞ ⎛ z ⎞
n=⎜
⎟ =⎜ ⎟
⎝ E ⎠ ⎝m⎠

2

where,
z is the z value (e.g., 1.645 for 90% confidence level, 1.96 for 95% confidence
level, and 2.575 for 99% confidence level);
σ is the standard deviation of the population;
E is the acceptable bound on the error or the “margin of error”
m is the margin of error expressed as a proportion of the standard deviation (e.g.,
.05 = + or – 5%, .07 = + or – 7%, and .1 = + or – 10%);
For the purposes of this study, we are using a 95% confidence level and a allowable error of +/10%.
The Finite Population Correction (FPC) factor is routinely used in calculating sample sizes for
simple random samples. In fact, many sample size formulas for simple random samples include
the FPC as part of the formula. It has very little effect on the sample size when the sample is
small relative to the population but it is important to apply the FPC when the sample is large
(10% or more) relative to the population. The sample size equation solving for n ' (new sample
size) when taking the FPC into account is:

n' =

n
1+

n
N

2

where,
n is the sample size based on the calculations above, and
N is population size.
The n’ estimate of sample size will then be multiplied by the estimated response rate to obtain
the actual number of surveys that will need to be mailed out over the next three years.
Zip Code - City
98595 - Westport, WA
98624 - Ilwaco, WA
97365 - Newport, OR
97444 - Gold Beach, OR
95531 - Crescent City, CA
94923 - Bodega Bay, CA
93442 - Morro Bay, CA
92629 - Dana Point, CA
TOTAL
Zip Code - City
98595 - Westport, WA
98624 - Ilwaco, WA
97365 - Newport, OR
97444 - Gold Beach, OR
95531 - Crescent City, CA
94923 - Bodega Bay, CA
93442 - Morro Bay, CA
92629 - Dana Point, CA
TOTAL

Surveys to
be mailed
638
518
718
670
736
286
726
746
5,038

Estimated
Response Rate
.6
.6
.6
.6
.6
.6
.6
.6
.6

Households to
be Surveyed
319
259
359
335
368
143
363
373
2,519

Surveys to be
mailed
105
64
335
189
289
58
274
371
1,685

Estimated
Response Rate
.7
.7
.7
.7
.7
.7
.7
.7
.7

Businesses to
be Surveyed
82
54
234
127
202
50
192
260
1,201

Visitors

Estimates of the total number of recreational visitors will be determined by collecting data on
total visitor occupancy in local hotels and then surveying respondents at numerous locations and
times throughout the city to determine the ratio of visitors staying in hotels and those not staying
in hotels. The total number of visitors (N) can then be determined by the following calculation:

TS
HS
Where HT is the total number of visitors staying in hotels, TS is the total number of visitors
surveyed, and HS is the number of visitors surveyed that stayed in hotels. The total number of
visitors staying in hotels will be determined from locally available hotel occupancy rates and by
surveying hotel guests.
N = HT *

3

This method is insensitive as to the ratio of locals to visitors responding so surveying can be
conducted in areas that are known to have a high proportion of visitors. The method is, however,
sensitive to the proportion of respondents who stay in hotels versus those that do not (i.e. day use
visitors). To account for this sampling will take place at multiple locations and at multiple times
throughout the day and evening. The survey instrument for visitors contains only four short
questions which are estimated to lake less than a minute to answer in total. If the respondent is
willing, the surveyor would ask the individual the four questions. The respondent would then be
asked if they would be willing to answer an additional 15 minute survey in exchange for a token
gift (NMFS tee shirt). If the respondent is not willing they will be asked if they would take the
survey home and complete it at their leisure, then return it in a prepaid envelope that is provided.
If they are not willing to do this, we thank them for their time and wish them a pleasant day.
Impartiality in selection for interviewing is stressed in interviewer training.
Using the same sample size calculation from above, the total number of visitor interviews needed
is as follows (potential universe size is estimated from Wen-Huei Chang and R. Scott Jackson,
Economic Impacts of Recreation Activities at Oregon Coastal and River Ports, ERD/EL TR-0312, U.S. Army Corps of Engineers, August 2003):
Zip Code - City

Visitors
Contacted

Response
Rate

1,056
1,047
1,067

98595 - Westport, WA
98624 - Ilwaco, WA
97365 - Newport, OR
97444 - Gold Beach,
OR
95531 - Crescent City,
CA
94923 - Bodega Bay,
CA
93442 - Morro Bay, CA
92629 - Dana Point, CA
TOTAL

Response
Rate

.6
.6
.6

Initial Visitor
Interviews to be
Conducted
633
628
640

.6
.6
.6

Longer Visitor
Interviews to be
Completed
380
377
384

1,042

.6

625

.6

375

1,042

.6

625

.6

375

1,067
1,067
1,067
8,453

.6
.6
.6
.6

640
640
640
5,072

.6
.6
.6
.6

384
384
384
3,043

Expected Response Rates:
Based on previous studies of households and businesses, a response rate of about 60% for
households and 70% for businesses is expected. These response rates are consistent with those
reported in Dillman (1974), Dillman (2000), and Fox et al. (1988). For visitors, it is expected
that at least 60% of the people contacted will be willing to answer the short four question survey.
It is then expected that at least 60% of the people who answer the initial questionnaire will
respond to the longer survey. These are similar to response rates that the U.S. Department of
Agriculture (USDA) Forest Service (2002) received with their National Visitor Use Monitoring
(NVUM) study. Additionally, the aforementioned Wen-Huei Chang and R. Scott Jackson study
also received a 60% response rate for visitors to Oregon ports.
Additionally, adherence to the Dillman method, the use of social exchange (see #3 below), and
garnered support from local officials and business leaders will support these minimum estimated
response rates.
4

3. Describe the methods used to maximize response rates and to deal with nonresponse.
The accuracy and reliability of the information collected must be shown to be adequate for
the intended uses. For collections based on sampling, a special justification must be
provided if they will not yield "reliable" data that can be generalized to the universe
studied.

Cooperation from industry representatives has been garnered as well as support of government
officials, commercial leaders, and the local population. A “social exchange” framework was
utilized to emphasize the potential benefits of responding (greater understanding of the local
economy and how to foster desired levels of economic growth) and to reduce the potential time
cost to the boat owners. Social exchange is mentioned by Dillman (2000) as a crucial
component of any social research survey and is intended to highlight the benefits of responding
to the survey while stating how the survey has been designed to reduce the time and effort costs
to the respondents.
A modified Dillman Method (Dillman 2000) will be employed to for the survey of the businesses
and households. This method utilizes the following components:
1.
Mailing of an information letter three to five days prior to the mailing of the
survey. This letter describes the kind of information that the survey will ask, describes
how the information will be used, and highlights the benefits of the survey to the
respondent.
2.
Three to five days after the information letter is mailed, the actual survey
instrument will be mailed with a detailed cover letter explaining the purpose of the study,
the expected benefits
3.
Two weeks after the survey is mailed, a thank you/reminder post card is mailed
4.
Two weeks after the post card is mailed, a replacement survey and cover letter
will be mailed to nonrespondents
5.
Two weeks after the replacement surveys are mailed, calls will be made to
nonrespondents asking if they have any questions about the study that we can help
answer for them
To reduce the possibility of unit non-response bias, a chi square test for structural differences
will be employed to ensure that non-respondents from the survey of businesses are not
systematically different from the population as a whole in known attributes such as business size
(as measured by number of employees) and business type (as measured by NAICS code). A
similar analysis will be performed on households to ensure that respondents are not
systematically different from non-respondents in known attributes such as household size and
income stratification.
Sample post-stratification methods will then be used to generate weighting classes if structural
differences are found.
For the visitor survey, a token gift will be offered to respondents willing to fill out the 15 minute
survey. The token gift will be a tee shirt designed for this project, the total value not exceeding
$5.
5

4. Describe any tests of procedures or methods to be undertaken. Tests are encouraged as
effective means to refine collections, but if ten or more test respondents are involved OMB
must give prior approval.

None
5. Provide the name and telephone number of individuals consulted on the statistical
aspects of the design, and the name of the agency unit, contractor(s), grantee(s), or other
person(s) who will actually collect and/or analyze the information for the agency.

Philip Watson, Ph.D.
Economist
NMFS
206-947-3107
Carl Lian, Ph.D.
Economist
NMFS
206-302-2414
Nancy Gove, Ph.D.
Statistician
NMFS
206-3022413
Don English, Ph.D.
Economist
US Forest Service
202-205-9595

Eric White, Ph.D.
Economist
US Forest Service
541-750-7422

6