Supporting Statement
A. Justification
Necessity of the Information Collection
The Bureau of Justice Statistics (BJS), of the U.S. Department of Justice, requests an extension of a currently approved collection, the National Crime Victimization Survey (NCVS) OMB No. 1121-0111, through July 2009. The Office of Management and Budget’s (OMB) current approval expires July 31, 2006. During the past several years, several modifications have been made to the NCVS. In some cases these modification included adding supplements, and in others, only sections of the existing instrument were modified. All of the changes that have been made to the NCVS are detailed in the Appendix B and were made with compliance with OMB Clearance procedures including submission of 83-c forms. This submission is for an extension of the current approval.
The NCVS, formerly the National Crime Survey (NCS), was initiated by the Law Enforcement Assistance Administration (LEAA) to fulfill the mandate set forth by Section 515b of Public Law 93-83 to collect, evaluate, publish, and disseminate information on the progress of law enforcement within the United States. The NCVS was transferred to the BJS in December 1979. Currently, Title 42, United States Code, Section 3732 of the Justice Systems Improvement Act of 1979, authorizes the BJS to collect statistics on victimization. The NCVS provides national data on personal and household victimization, both reported and not reported to police. Together with statistics on crimes reported to law enforcement agencies across the country published by the Federal Bureau of Investigation (FBI), the two programs provide a more complete examination of the nation’s crime problems than either could do alone.
The NCVS is the only source of annual national data on a number of policy relevant subjects related to criminal victimization, including family violence, domestic violence, drugs and alcohol and crime, injury from victimization, the cost of crime, carjacking, and reporting to police. Other policy relevant topics covered by the survey include weapon use in crime and victimization of subpopulations such as the elderly and juveniles.
Per the terms of the OMB Clearance approval for the Stalking Supplement to the NCVS in July, 2005, BJS and the Census Bureau are reviewing the questions on the NCVS-2 Incident Report used to obtain information about the perceived race of offenders. Currently, the questions ask “Were the offender(s) White, Black, or some other race?” If the respondent marks “some other race,” space for a write-in entry is provided, but specific race categories are not extracted from these entries.
Collecting data on race of offender has always been more problematic than collecting data on race of victim which is self-reported by the respondent. In 2003, 3% of victims of violence committed by lone offenders and 9% by multiple offenders were unable to provide any information about the race of the offender. For robberies involving injury by lone offenders, 7% of victims did not know whether the offender was white, black or some other race. When multiple offenders committed a robbery that caused injury, 17% of victims could not provide this basic information about the race of any of the offenders.
It is understandable that there are many situations in which the victim is not able to get a good view of the offender/offenders. The crime may occur during the night, the offender/offenders may use disguises to make identification difficult, or the victim may be too preoccupied with self protection to observe much about the offender and other similar reasons. The information that victims can provide about offenders does present useful insights about the nature of crime. For example, NCVS data show that most crime is intraracial. In 2003, about 2/3 of white victims and ¾ of black victims of violent crime reported that the offenses were committed by offenders perceived to be of their same race.
BJS and Census have initiated a study to examine the write-in entries to determine whether there are sufficient numbers of cases for non-specified racial groups to revise the question to be more inclusive of all racial categories. Because these questions provide information about offenders based on perceptions of respondents, care must be taken to avoid asking respondents to go beyond abilities to provide information. For this reason, there are no plans to ask about perceptions about offenders’ ethnicity, since this identification cannot be made solely by visual cues. The decision about revising the questions on race of offender will be made once the study has been completed. BJS will provide OMB with the results of the study and the proposed revisions to the NCVS questionnaire. If revisions are made, they will be implemented at the next opportunity, possibly in January, 2007. As a result, BJS requests a variance at this time for collecting detailed information on race of offender.
Needs and Uses
The NCVS provides information on crimes that are of interest to the general public, government agencies, and the criminal justice community.
Because the NCVS is the only ongoing vehicle for producing data related to a broad spectrum of subjects related to crime and crime victimization, legislators and policy makers at all levels of government increasingly use the NCVS data. For example, Congressional debates on bills concerning victim compensation, gun control, crime and unemployment, and development of crime prevention programs for the elderly have used the NCVS data. Also, the Presidential Task Force on Victims of Crime made extensive use of NCVS data and Federal executive departments have used the NCVS data to support development of programs related to a broad variety of issues, including violence against women, intimate partner violence, school crime, juvenile justice and crime against the elderly. Some specific examples of government agencies that make use of the NCVS data include the following:
Community groups
Use the data to develop neighborhood watch programs.
Law enforcement agencies
Use the NCVS findings for training purposes and the findings can be seen in crime prevention public service announcements and in crime documentaries. Law enforcement agencies in various cities also use the NCVS data to increase:
Citizen cooperation with officials in deterring and detecting crime.
Special police strike forces to combat those crimes which the survey indicates as being most prevalent, and
Street and park lighting programs in those areas with the highest reported crime rates.
Print and broadcast media
The media have become increasingly familiar with the NCVS data. Findings from the NCVS now appear regularly in a wide variety of contexts on television, radio, and in print when reporting on a host of crime-related topics.
Other uses of the NCVS
There are other reasons why data users want the crime victimization information produced from the NCVS. Some of the reasons include:
Planning for public education programs, police patrol strategies, and new communities and housing projects. This type of planning requires knowledge of the characteristics of victimized persons and households, as well as when and where victimizations occur.
Conducting feasibility studies and planning programs for the restitution and compensation to victims of crime. These studies and programs require information on the nature and extent of injury and loss that results from criminal victimization.
Assessing the need for property identification programs. These programs require information on the amount of property recovered after burglaries and thefts.
Understanding more about the nature and extent of biases in police data on known offenses. These studies require knowledge of the levels of nonreporting to the police, together with information on the kinds of victimization that are disproportionately not reported to the police.
REPORTS
and PAPERS
The
BJS has a special analysis group that analyzes the data and produces
several types of publications on a periodic basis. Some of the past
publications released from this survey include:
Criminal Victimization in the United States
Changes in Criminal Victimization
Violent Victimization of College Students
Crime and the Nation’s Households
Other reports have been released on the following topics:
Crimes Against Persons Age 65 or Older
Female Victims of Violent Crime
Hispanic Victims of Violent Crime
Injuries From Violent Crime
If the NCVS program were discontinued, executive and legislative branch policy makers would no longer have crime and victim-related information available when making decisions on formulating legislation except from the FBI data that lack the demographic information that makes the NCVS data so valuable. Also, there would be no reliable measure of changes in the rate of serious crime for the United States that include crimes not reported to the police.
Information quality is an integral part of the pre-dissemination review of information disseminated by the Census Bureau (fully described in the Census Bureau's Information Quality Guidelines). Information quality is also integral to information collections conducted by the Census Bureau, and is incorporated into the clearance process required by the Paperwork Reduction Act. Additionally, BJS maintains a rigorous quality control process as documented in its Data Quality Guidelines.
3. Use of Information Technology
Respondents are households and individuals. The Census Bureau collects the data from in-person and telephonic interviews. Currently about 22 percent of the telephone interviews are conducted with a computer-assisted telephone interviewing (CATI) system from the Census Bureau’s centralized telephone interviewing facilities. For the remaining 78 percent of the sample, beginning in July 2006, field representatives will no longer conduct the NCVS interviews using paper-and-pencil interviewing (PAPI) methods. Instead, the interviews will be conducted using computer-assisted personal interviewing (CAPI) methods whereby field representatives use a laptop computer to display questions and accept responses. As a result, 100 percent of the data will be collected electronically beginning in July and by the time for which this extension is being requested.
Cost was one of the primary reasons for deciding to convert the NCVS to a fully automated survey. As data collection for all other demographic surveys within the Census Bureau fully utilize automated data collection methods, maintaining a PAPI collection for the NCVS has become more expensive. Additionally, a fully automated collection enables us to implement requests for new content and new methods into the survey faster. Additional benefits from utilizing a fully automated collection include raising the quality of the NCVS data, streamlining the processing systems since there will no longer be a need for a dual systems to accommodate two different modes of data collection, and eliminating data differences resulting from two different interviewing methods. Furthermore, due to the nature of the survey, it is not possible to utilize any other forms of information technologies to reduce respondent burden.
Efforts to Identify Duplication
The Census Bureau's current surveys' sampling frame is the universe for the NCVS sample. The NCVS does not duplicate any other effort in the field. The BJS has studied and continues to study the relationship of the NCVS data to the Uniform Crime Reports (UCR) data. The BJS conducts these studies through the BJS NCVS redesign projects and a joint BJS-FBI UCR evaluation project to find ways to make the data from each more complementary.
There is no other information available to prepare national crime statistics based on the demographic characteristics of victims and victimized households, regardless of whether the victimization was reported to the police.
Minimizing Burden
N/A. The NCVS is a household-based sample and does not impact small businesses or small entities.
Consequences of Less Frequent Collection
To produce a regular series of data on crime victimization requires regular data collection. A change to a less frequent data collection would require using a longer reference period. The change to longer reference periods is likely to reduce data quality because research has shown that memory decay increases as the length of the reference period increases. Furthermore, if the NCVS program were discontinued, executive and legislative branch policy makers would no longer have crime and victim-related information available when making decisions on formulating legislation except from FBI data that lack the demographic information that makes the NCVS data so valuable. Also, there would be no reliable measure of changes in the rate of serious crime for the United States that include crimes not reported to the police.
7. Special Circumstances
N/A. Collection is consistent with the guidelines in 5 CFR 1320.9.
8. Consultations Outside the Agency
Mr. Lawrence S. McGinn, Mr. Robert A. Tinari, Ms. Helen S. Montagliani and Mr. Charles H. Alexander, Census Bureau; Dr. Albert D. Biderman, Dr. James P. Lynch and Dr. Elizabeth Martin, formerly of Bureau of Social Science Research (BSSR); Dr. Robert M. Groves, Survey Research Center, University of Michigan.
Members of the NCVS Redesign Consortium Advisory Board included Professor Wesley Skogan, Center for Urban Affairs, Northwestern University; Professor Albert Reiss, Institute for Social and Policy Studies, Yale University; and Professor Richard Sparks, School of Criminal Justice, Rutgers University; Dr. Thomas Jabine; Mr. James Wetzel, Chief, Center for Demographic Studies, Census Bureau; Professor Colin Loftin, Institute of Criminology and Criminal Justice, University of Maryland; Dr. Harry Scarr, Office of Economic Affairs, U.S. Department of Commerce; Professor Gilbert Geis, Program in Social Ecology, University of California; Mr. Gregory King, Victim Witness Assistance Program; Dr. Anne Schneider, Department of Political Science, Oklahoma State University; Dr. Cynthia Turnure, Chemical Dependency Program Division, Department of Public Welfare; Dr. Paul Zolbe, Chief, Uniform Crime Reporting Program, FBI; Chief Allen Andrews, Superintendent of Police, Peoria Police Department; Dr. Charles Wellford, Dean, Institute of Criminology and Criminal Justice, University of Maryland; Professor Stephen E. Fienberg, Department of Statistics, Carnegie-Mellon University;
Dr. Barbara Bailar, Associate Director for Statistical Standards and Methodology, Census Bureau; Dr. David Seidman, Wilmer, Cutler and Pickering; Dr. Daniel Horvitz, Vice President, Research Triangle Institute, Statistical Science Group; Mr. Michael Block, University of Arizona; Dr. Harold Nisselson, Senior Statistical Advisor, WESTAT; Mr. Jeffrey Roth, WESTAT; Dr. James Collins, Research Triangle Institute, Center for Study of Social Behavior; and Mr. Ralph Folsom, Research Triangle Institute, Center for Study of Social Behavior.
Members of the American Statistical Association Committee on Law and Justice Statistics who recommended the additional changes to improve the estimates of the incidence of rape in the NCVS include Dr. Charles Wellford, Professor and Director, Institute of Criminal Justice and Criminology, University of Maryland; Dr. David Cantor, WESTAT; Dr. Colin Loftin, Institute of Criminology and Criminal Justice, University of Maryland; and Dr. Diane Saphire, Associate Professor, Trinity University. Other study group members included Dr. Jane Burnley, Office of Justice Programs, U.S. Department of Justice, Dr. Ann Coker, Director, Department of Epidemiology, University of South Carolina; Dr. Lorie A. Fridell, Assistant Professor, School of Criminology, Florida State University; Dr. Dean Kilpatrick, Director, Crime Victims Research and Treatment Center, Charleston, South Carolina; and Dr. Mark Warr, Department of Sociology, University of Texas.
In 2005, BJS funded a panel of survey researchers and criminologists to explore potential cost saving changes to the survey. Participants in this effort included: Dr. Janet Lauritsen, University of Missouri-St. Louis; Dr. David Cantor, Research Associate Professor, Joint Program in Survey Methodology, University of Maryland, and Westat; Dr. Robert Groves, Professor of Sociology and Director of the Survey Research Center at the Institute for Social Research, University of Michigan; Dr. Sharon Lohr, Distinguished Professor of Statistics, Arizona State University, Tempe; Dr. James P. Lynch, Professor, John Jay College of Criminal Justice, NY; Dr. Trivellore Raghunathan, Professor of Biostatistics, Research Professor at the Institute for Social Research, University of Michigan; and Dr. Roger Tourangeau, Director of the Joint Program in Survey Methodology (University of Maryland) and Research Professor in the Institute for Social Research at the University of Michigan.
9. Paying Respondents
N/A. Payment or gifts to respondents is not provided in return for participation in the survey.
10. Assurance of Confidentiality
All NCVS information about individuals or households is confidential by law--Title 42, United States Code, Sections 3789g and 3735 (formerly Section 3771) and Title 13, United States Code, Section 9. Only Census Bureau employees sworn to preserve this confidentiality may see the survey responses. Even BJS as the sponsor of the survey, is not authorized to see or handle the data in its raw form. All unique and identifying information is scrambled or suppressed before it is given to BJS to analyze. Data is kept in secure environments and in restricted access locations within the Census Bureau. All data given to BJS must meet the confidentiality requirements set forth by the Disclosure Review Board at the Census Bureau.
In a letter signed by the Director of the Census Bureau, sent to all participants in the survey, respondents are informed of this law and assured that it requires the Census Bureau to keep all information provided by the respondent confidential. The letter also informs respondents that this is a voluntary survey. Furthermore, in addition to the legal authority and voluntary nature of the survey, the letter informs respondents of the public reporting burden for this collection of information, the principal purposes for collecting the information, and the various uses for the data after it is collected which satisfies the requirements of the Privacy Act of 1974.
11. Justification for Sensitive Questions
The NCVS asks about experiences that may be sensitive for some respondents. Given the
objective of the NCVS--to estimate the amount of victimization in the Nation--this is inevitable. The importance of estimating crime levels, as well as the potential value of detailed information about victimization for designing crime prevention strategies, will be explained to any respondent who seems hesitant to answer. We have structured the questions and interviewer application of them to lessen their sensitivity. All respondents have the option of refusing to answer any question.
12. Estimate of Hour Burden
noninterviewed households in the actual survey. The estimates are based on 2005 interview/noninterview counts.
Reinterview Reinterview TOTAL
Interviewed Noninterviewed (Interviews) (Noninterview)
No. of respondents 77,000 13,500 3,400 1,135 95,035
(households)
No. of responses 2 2 1 1
per year
Total annual responses 154,000 27,000 3,400 1,135 185,535
(households)
Est. number of hours .381 .120 .206 .005
Per response
Est. total hours of 58,674 3,240 700 6 62,620
respondent
The time estimates are based on the results of a time study using the near-term questionnaire and on a pretest that was conducted in June 1987 using the long-term NCVS questionnaire.
14. Cost to the Federal Government
There are no capital or start-up costs associated with the data collection.
The estimated annual cost to the Federal Government for the basic NCVS is $20.5 million in FY 2006. The Census Bureau handles all aspects of collecting and preparing data for analysis at an annual cost of $19.7 million. The largest share of costs is the labor for the interviewers who collect data from respondents ($15.5 million). Data processing is $5.4 million and sampling is $3.5 million. , and laptop acquisition is $500,000. The BJS staff time costs $750,000, and laptop acquisition to collect the data in the amount of $500,000 is being supported by BJS. The BJS of the U.S. Department of Justice bears all costs of the survey.
15. Reason for Change in Burden
The decrease in respondent burden hours is due to the reduction in the NCVS sample that has occurred since the previous submission. This reduction in sample was due to budgetary constraints and a reduction in funds available for the NCVS.
16. Project Schedule
The BJS releases information collected in the NCVS in a variety of formats. Each spring
BJS releases a report providing annual estimates from the survey, including rates and counts of violent and property crime, characteristics of crimes and victims, year to year change estimates and trend estimates.
The BJS annually produces a detailed annual report on its website that provides crime rates by type of crime, victim and offender characteristics, incident characteristics, and other detailed information on an basis. This web document includes links to spreadsheets providing users the ability to further analyze the survey data. Since 2003, the BJS has provided an advanced web based indexing format that greatly facilitates users accessing tables in the report.
In addition, each year the BJS releases a number of in-depth analytical monographs and other papers that provide information on some of the broad range of topics covered in the survey. These reports cover such topics as victimization and victim race, injuries from violent crime, school crime, intimate partner violence, age patterns in violent victimization, Hispanic victims of crime, third party involvement in crime, and reporting to police of rape and sexual assault.
Interviewing for the national sample begins on the first of each month. The CATI interviewing is conducted during the first two and one-half weeks of every interview month. The PAPI interviewing, which comprises the remaining 78 percent of assigned sample cases monthly, is conducted over the entire interview month. (Beginning in July 2006, this component will be interviewed using CAPI.) Data processing is conducted on both a monthly and quarterly basis. Because the survey uses a 6-month recall period, crime incidence data for a given calendar year are not fully collected until June of the following year. However, annual estimates are produced and published based on a collection year rather a data year basis starting with the 1996 data. Annual collection year estimates are provided to the BJS approximately in March of each year.
Data from the survey are archived at the Inter-university Consortium for Political and Social Research (ICPSR) at the University of Michigan. Researchers can download public use files of the NCVS data and codebooks to conduct their own analyses. The public use files are produced by the Census Bureau. All information that might identify individual respondents to the survey is removed from the files sent to the ICPSR.
17. Request to Not Display Expiration Date
N/A. The OMB number is displayed on all public-use forms, including electronic instruments, used to collect information from the public.
18. Exceptions to the Certification
N/A. There are no exceptions to Certification for Paperwork Reduction Act
Submissions. Collection is consistent with the guidelines in 5 CFR 1320.9.
B. Collections of Information Employing Statistical Methods
1. Universe and Respondent Selection
Interviewers are able to obtain interviews with 84-86 percent of the household members in
91 percent of the occupied units in sample in any given month. This is an ongoing survey
that is in the filed 12 months of the year.
The national sample consists of approximately 62,000 designated addresses located in 228
stratified PSUs throughout the United States. The sample consists of six parts, each of
which is designated for interview in a given month and again at 6-month intervals. We
redesigned the NCVS sample based on the 1990 Decennial Census of Population and
Housing. Beginning in 1995, the new sample addresses being introduced were selected
based on the new design. Housing newly constructed since that census is also sampled. In
October 1996, we reduced the NCVS sample because of budgetary constraints. We
permanently dropped 42 nonself-representing (NSR) primary sampling units, or about
12 percent of the entire sample. In July 1996, as another measure to contain costs,
telephone interviewing increased as all rotations except the first were designated for
telephone interviews. In April 2002, we implemented a 4 percent sample reduction across
all PSUs to reduce sample creep and to curtail rising Field costs. Beginning in 2005, new
sample addresses were introduced based upon the 2000 Decennial Census of
Population and Housing. Newly constructed housing since that census were also sampled.
To offset the increase in survey costs due to the phase-in of the 2005 sample design, we implemented a 10 percent sample cut in April 2005 and an additional 16 percent cut in
January 2006. These sample cuts were made to the 1990 design sample only.
The NCVS uses a rotating sample. A representation of the rotation plan appears as an
attachment (NCVS-551). The sample consists of six groups for each month of enumeration. Each of these groups stays in the sample for an initial interview and six subsequent interviews. The initial interview is essentially a bounding interview, which establishes a reference period, reduces telescoping into the reference period, and enables the interviewer to avoid recording duplicate reports on subsequent visits. During the course of a 6-month period, we interview a full sample of six rotation groups--one-sixth each month. In addition, one rotation group enters the sample for its bounding interview each month.
Each interview period the interviewer completes or updates the household composition component of the NCVS interview and asks the crime screen questions for each household member 12 years old or older. The interviewer then completes a crime incident report for each reported crime incident. Each household member provides the information by self-response.
The first contact with a household is by personal visit. For the second through seventh visits, we use telephone interviews whenever possible. Approximately 64 percent of the interviews conducted each month are by telephone.
Procedures for Collecting Information
The NCVS is designed to calculate national estimates of crimes for the target population - the noninstitutional resident population aged 12 years and older. The list used to reach the target population is the addresses of all living quarters in the U.S. compiled from the most recent decennial census and lists of housing units constructed since that most recent decennial census. Sample selection for the NCVS has three stages: the selection of primary sampling units or areas known as PSUs, the selection of address units in sample PSUs, and the determination of persons and households to be included in the sample. Survey estimates are derived from a stratified, multi-stage cluster sample. The PSUs composing the first stage of the sample are formed from counties, groups of adjacent counties, or large metropolitan areas based upon data from the decennial census. The larger PSUs are included in the sample automatically and are considered to be self-representing (SR) since all of them are selected with certainty. The remaining PSUs, called NSR because only a subset of them are selected, are combined into strata by grouping PSUs with similar geographic and demographic characteristics, as collected in the decennial census from which the sample is drawn. For the NCVS, administrative crime data are also used to stratify the PSUs.
SAMPLING
Stage 1. Defining and Selection of PSUs:
Defining PSUs - Formation of PSUs begins with listing counties and independent cities in the target area. For the NCVS, this is the entire country. The counties are either grouped with one or more contiguous counties to form PSUs or are PSUs all by themselves. The groupings are based on certain characteristics such as total land area, current and projected population counts, large metropolitan areas, and potential natural barriers such as rivers and mountains. The resulting county groupings are called PSUs.
After the PSUs are formed, the large PSUs and those in large urban areas are designated self-representing (SR). The smaller PSUs are designated non self-representing (NSR). Determining which PSUs are considered small and which are large depends on the survey’s SR population cutoff. A SR PSU must be large enough in population to support at least one field representative with a full workload of approximately 32 cases. For the NCVS, all PSUs with population over 223,176 were labeled SR.
Stratifying PSUs - The NSR PSUs are grouped with similar NSR PSUs within region (Northeast, South, Midwest, West) to form strata. Each SR PSU forms its own stratum. The data used for grouping the PSUs consist of decennial census demographic data and administrative crime data. As was stated earlier, NSR PSUs are grouped to be as similar or homogeneous as possible. Just as the SR PSUs must be large enough to support a full workload so must each NSR strata be of that size. The most efficient stratification scheme is determined by minimizing the between PSU variance and the within PSU variance.
Selecting PSUs - The SR PSUs are automatically selected for sample or “selected with certainty.” One NSR PSU is selected from each grouped stratum. The NSR PSUs are sampled with probability proportional to the population size using a linear programming algorithm. Initially, the NCVS design for collection year 2004 consisted of 93 SR PSUs and 152 NSR PSUs. However, a sample reduction was necessary several years ago for budgetary reasons and the resulting design now consists of 93 SR PSUs and 110 NSR PSUs. (Sample cuts in NSR PSUs are more cost-effective since entire workloads can be eliminated.)
Stage 2. Preparing Frames and Sampling Within PSUs
Frame Determination - To ensure adequate coverage for the target population, the Census Bureau defines and selects sample from four address lists called frames: the unit frame, the area frame, the group quarters frame, and the new construction or permit frame. Each address in the country is assigned to one and only one of these frames. Which frame an address is assigned to depends on four factors: 1) what type of living quarters are at the address, 2) when the living quarters were built, 3) where the living quarters were built, and 4) how completely the street address was listed. The main distinction between the frames are the procedures used to collect the survey data from that sample address.
Two types of living quarters are defined in the decennial census. The first type is a housing unit. A housing unit (HU) is a group of rooms or a single room occupied as separate living quarters or intended for occupancy as separate living quarters. A housing unit may be occupied by a family or one person, as well as by two or more unrelated persons who share the living quarters. Before the 2000 decennial census, separate living quarters were defined as a space in which the occupants live and eat separately from all the other persons on the property and have direct access to their living quarters from the outside or through a common hall or lobby as found in apartment buildings. Beginning with the 2000 decennial census, the criteria for separate living quarters are that the occupants must live separately from any other individuals in the building and have direct access from outside the building or through a common hall or entry. Eating separately is no longer a criterion.
The second type of living quarters is group quarters (GQ). Group quarters are living quarters where residents share common facilities or receive formally authorized care. Table 3.1 shows the population distribution by frame in the 2000 decennial census. About 3 percent of the population counted in the 2000 census resided in group quarters. Of those, less than half resided in non-institutionalized group quarters. About 97 percent of the population counted in the 2000 census lived in housing units.
Within-PSU Sampling - All the Census Bureau’s continuing demographic surveys, such as the NCVS, are sampled together shortly after the most recent decennial census. This takes advantage of newly available census data that shows population growth and demographic changes, as well as updated unit address lists. Roughly a decade’s worth of sample is selected at that time. Selection of samples is done one survey at a time (sequentially) and one frame at a time (independently). Each survey determines how the unit addresses within the frame should be sorted prior to sampling. For the NCVS, each frame is sorted by geographic variables. A systematic sampling procedure is used to select living units from each frame. For the unit and the GQ frames, actual unit addresses are selected and reserved for the NCVS. In the area frame, a specified number of living quarters in a specific geographic location are promised to the NCVS and after the address listing operation in that geographic area, the specific unit addresses are assigned. Similarly in the permit frames, empty place holders are selected for the NCVS within the PSU. Then over time as new permits are issued, the place holders are replaced with actual newly built housing units/addresses.
Addresses selected for a survey are removed from the frames, leaving an unbiased or clean universe behind for the next survey that is subsequently sampled. By leaving a clean universe for the next survey, duplication of addresses between surveys is avoided. This is done to help preserve response rates by limiting the number of units falling into more than one survey sample.
Stage 3: Sample Within Sample Addresses
The last stage of sampling is done during initial contact of the sample address during the data collection phase. For NCVS, if the address is a residence and the occupants agree to participate, then every person aged 12 or older who lives at the resident address is interviewed. There are procedures to determine who lives in the sample unit and a household roster is completed with their name and other demographic information. If someone moves out (in) during the interviewing cycle, they are removed from (added to) the roster.
DATA COLLECTION
Each housing unit selected for the NCVS remains in the sample for three years, with each of seven interviews taking place at 6-month intervals. Respondents are asked to report crime experiences occurring in the six months preceding the month of interview. Research has shown that respondents are able to recall more accurately an event which occurred within three months of the interview rather than one which occurred within six months; they can recall events over a 6-month period more accurately than over a 12-month period. However, a shorter reference period would require more field interviews per year, increasing the data collection costs significantly. These increased costs would have to be balanced by cost reductions elsewhere (sample size is often considered). Reducing sample size however, reduces the precision of estimates of relatively rare crimes. In light of these trade-offs of cost and precision, a reference period of six months is used for the NCVS, and some degree of response error is accepted.
3. Methods to Maximize Response
Several steps are taken to encourage response and maximize response rates:
● An advance introductory letter is mailed to sampled households from the Director of the Census Bureau explaining the authority for and purposes of the survey to the household before the interviewer’s visit or call.
● Field representatives carry cards and portfolios identifying them as Census Bureau employees.
● The Census Bureau trains the interviewers to obtain respondent cooperation and instructs them to make repeated attempts to contact respondents and complete all interviews. The interviewer obtains demographic characteristics of noninterview persons and the race of noninterview households for use in the adjustment for nonresponse.
● Potential respondents are assured that their answers will be held in confidence and used only for statistical purposes.
● Senior field representatives and supervisors may be called in to convert refusals.
Performance guidelines were established for the NCVS in an effort to maximize response rates. These guidelines are used by the regional offices and telephone centers as examples of how they might measure performance.
The response rate for the NCVS for 2005 was 91 percent. The response rate was calculated using the following formula: Household response rate = Sum of all interviewed households/(sum of all interviewed households + sum of all Type A noninterview households). As part of their job, interviewers are instructed to keep noninterviews to a minimum. Maintaining a low nonresponse rate involves the interviewer’s ability to enlist cooperation from all kinds of people and to contact households when people are most likely to be home. As part of their initial training, interviewers are exposed to ways in which they can persuade respondents to participate as well as strategies to use to avoid refusals. Furthermore, the office staff makes every effort to help interviewers reduce their noninterviews by suggesting ways to obtain an interview, and by making sure that sample units reported as noninterviews are in fact noninterviews. Also, survey procedures permit sending a letter to a reluctant respondent as soon as a new refusal is reported by the interviewer to encourage their participation and to reiterate the importance of the survey and their response.
4. Tests of Procedures or Methods
Long-term changes would have a substantial impact on the crime rates produced by the NCVS. These changes were gradually phased-in so that we could measure their effect on the NCVS crime rates, test the procedures, and resolve minor problems prior to full implementation.
Furthermore, a group, composed of members of the American Statistical Association Committee on Law and Justice Statistics, examined the strengths and limitations of the measurement of rape by the National Crime Survey and recommended additional changes to the long-term questionnaire. These changes, which were implemented in July 1991, were expected to improve the estimates of the incidence of rape in the NCVS.
Pretests of the long-term changes were conducted in the Washington, D.C. area in June and September 1987, and nationwide in February, March, August, and September 1988 (OMB No. 1121-0127). The long-term questionnaire was implemented in 5 percent of the NCVS sample starting in January 1989, 10 percent of the sample starting in January 1990, and 50 percent of the sample starting in January 1992. Full implementation was in July 1993.
Since July 1993, subsequent changes to the survey content, such as the inclusion of questions on hate crime, disability, computer crime, and the identity theft, were either cognitively tested or an expert review of the survey questions was conducted to ensure the wording and sequence of the question items were appropriate.
The conversion of the NCVS to a fully automated survey entails various testing of the survey instrument and control systems. In late 2005, testing of the NCVS CATI/CAPI survey began and will continue through the first half of 2006. Testing includes a full instrument test of all parts of the instrument including the systematic checking of instrument output; multiple systems tests of all control systems that will be used for production; a hothouse in which interviewers come in from the field and review the instrument with input; a dress rehearsal (test) of all production systems but using test data and conducted by real interviewers who may interview live respondents taken from the NCVS reserve sample or do mock interviews; a verifications test to ensure that all changes/problems reported in Systems Test are corrected.
5. Contacts for Statistical Aspects and Data Collection
The Census Bureau will collect all the information. Ms. Karen King, of the Demographic
Statistical Methods Division of the Census Bureau provided consultation on the statistical
and methodological aspects of NCVS. Ms. King can be reached by telephone on
301-763-1974. Ms. Marilyn Monahan heads the Crime Surveys Branch of the
Demographic Surveys Division, which manages and coordinates the NCVS. Ms. Monahan can be reached by telephone on 301-763-5315.
Appendix A
NCVS Timeline and Forms
Timeline
Frequency of Data Collection |
J |
F |
M |
A |
M |
J |
J |
A |
S |
O |
N |
D |
1/6 of sample |
X |
|
|
|
|
|
X |
|
|
|
|
|
1/6 of sample |
|
X |
|
|
|
|
|
X |
|
|
|
|
1/6 of sample |
|
|
X |
|
|
|
|
|
X |
|
|
|
1/6 of sample |
|
|
|
X |
|
|
|
|
|
X |
|
|
1/6 of sample |
|
|
|
|
X |
|
|
|
|
|
X |
|
1/6 of sample |
|
|
|
|
|
X |
|
|
|
|
|
X |
Forms Used with All Sampled Households
(completed by interviewers in-person or on the phone)
Form Number |
Title |
Description |
Frequency |
NCVS-500 |
Control Card |
“Control Card” Lists a roster of all persons living in the household with ages and other characteristics to help interviewer determine who should be interviewed. |
Monthly (2x/yr per household) |
NCVS-1 |
Basic Screen Questionnaire |
“Screener” Screens for crime incidents. |
Monthly (2x/yr per household) |
NCVS-1(SP) |
Spanish Basic Screen Questionnaire |
“Spanish Screener” Spanish translation of NCVS-1. |
Monthly (2x/yr per household) |
NCVS-1A |
Personal Characteristics |
“Additional Screener” Used to supplement the Screener if there are more than three members in the household. |
Monthly (2x/yr per household) |
NCVS-2 |
Incident Report |
“Incident Report” Collect detailed information about each incident identified in the screener |
Monthly (2x/yr per household) |
NCVS-2(SP) |
Crime Incident Report |
“Spanish Incident Report” |
Monthly (2x/yr per household) |
NCVS-7 |
Noninterview Record |
“Noninterview record” Records reasons why an interview was not able to be completed. |
Monthly (2x/yr per household) |
Forms Used with Some Households
(Standard forms used by interviewers upon request to provide more information)
NCVS-110 |
NCVS Fact Sheet |
“Fact Sheet” This is a brochure for the field representatives to give to respondents if they have questions about the NCVS. |
As needed |
NCVS-554 |
Field Representatives Information Card Booklet |
“FR Booklet” Contains answers to frequent response categories that may need further explanation. |
As needed |
NCVS-554(SP) |
Field Representative’s Information Card Booklet (Spanish) |
“Spanish FR Booklet” Spanish translation of NCVS-554 |
As needed |
NCVS-541 |
Reinterview Basic Screen Questionnaire |
“Reinterview screener” Used by senior field representatives to evaluate the performance of a small set of field representatives. |
As needed |
NCVS-545 |
Reinterview Questionnaire for Original Survey Noninterviews (Type B and C) |
“Reinterview for Noninterviews” Used by senior field representatives to verify the ineligibility of residents. |
As needed |
Forms mailed as Letters
NCVS-572(L) |
Introductory letter |
“Introductory letter” Introductory letter mailed to households prior to data collection. |
Incoming households |
NCVS-593(L) |
Thank-you letter |
“Thank-you letter” Letter sent to households that completed an interview. |
Monthly (2x/yr per household) |
NCVS-593(L)SP |
Spanish thank-you letter |
“Spanish thank-you letter” Spanish translation of the thank-you letter. |
Monthly (2x/yr per household) |
NCVS-573(L) |
Follow-up letter |
“Follow-up letter” Letter sent to households in rotations 2-7 and includes Frequently Asked Questions about the National Crime Victimization Survey. |
Monthly (2x/yr per household) |
NCVS-594(L) |
Final letter |
“Final letter” Final letter sent to thank households after the 7th enumeration period. |
Outgoing households |
NCVS-594(L)SP |
Spanish final letter |
“Spanish final letter” Spanish translation of the final letter. |
Outgoing households |
Appendix B
OMB approved revisions to the NCVS
The NCVS has been used as the vehicle for a number of supplements to provide additional information about crime and victimization. The School Crime Supplement was conducted for the National Center for Education Statistics in 1989 and 1995, and every two years since 1999. A Workplace Risk Supplement was conducted for the National Institute for Occupational Safety and Health in 2002. A supplement was added in 2001 to obtain information about public contacts with the police. This supplement, which has been used to inform the nation on the subject of racial profiling in traffic stops, is conducted every three years basis. A supplement to examine stalking behaviors was implemented in January-June, 2006.
The NCVS has been used as the vehicle for developing questions to obtain information about a variety of initiatives related to crime and crime victimization. In 1999, a set of questions was added to the survey to obtain information about hate crime victimization. In 2000, in response to a Congressional mandate, questions were added on a test basis to collect information about the victimization of people with developmental disabilities. The Census Bureau, in conjunction with the BJS, developed questions to collect this information as part of the NCVS beginning in July 2000. Also, beginning in July 2000, questions pertaining to the respondent's lifestyle and home protection were removed from the NCVS to enable adding questions without increasing respondent burden.
Per Executive Order 13221 signed by the President on October 16, 2001, the BJS worked to develop questions designed to elicit information from NCVS respondents about the vulnerability to as well as occurrences of computer related crime. With the ever expanding growth and use of the internet, including a rapid growth of internet related commerce, there is growing concern about vulnerability of people to a variety of offenses related to its use. Such offenses include attacks by computer viruses, fraud in purchasing online, threats via email and unrequested lewd or pornographic emails.
In addition to adding the computer crime questions to the NCVS, the BJS requested implementation of revised employment questions and the expansion of the victim-offender relationship answer categories on the NCVS-2, Crime Incident Report. The new employment questions are used to obtain more detailed information about the industry and occupation of employed respondents who were victims of crime. The revised answer categories for the victim-offender relationship questions provide more detailed information about employee-employer type relationships of victims to their offenders.
Existing questions on the survey were also revised during the past few years. The BJS also directed implementation in January 2003 of several changes data collected from the NCVS-500 Control Card and the NCVS-1 Basic Screen Questionnaire for the NCVS in order to comply with the OMB’s new guidelines for collecting data on race and ethnicity from the respondent. These changes included:
Replacing the existing single-response race question with a multiple-response race question and allowing a maximum of four categories (races) to be selected by the respondent.
Incorporating revised race answer categories for the race question.
Modifying the question wording of the current ethnicity question.
Asking the ethnicity question prior to the race question, rather than after the race question.
At the request of the BJS, in 2003 the Census Bureau replaced the education questions, “Education-highest grade” and “Education-complete that year?” with a single question that asks about “Education-highest grade completed?” This new question included expanded answer categories for the 12th grade high school educational level and higher educational degrees as well. In January 2004, two new questions were added to determine if a sample unit is located within a gated/walled or restricted access community. Also, at this time, two new questions were added to the crime incident report to collect information about the number of guns stolen and number of other firearms stolen.
In July 2004, the computer crime questions were removed from the survey and questions about identity theft were added. These questions on use or unauthorized use of credit cards, existing accounts, or personal information were added to the NCVS-1, Basic Screen Questionnaire in an effort to identify better ways to help victims of identity theft and to find more effective methods of eliminating this type of crime.
Finally, as research shows that pregnant women may be at a higher risk of being a victim of violent crime, in July 2005 a question was added to the NCVS crime incident report to determine the pregnancy status, of all female respondents age 18 to 49, at the time the incident occurred.
| File Type | application/msword |
| File Title | Supporting Statement |
| Author | MONAH002 |
| Last Modified By | Scarbora |
| File Modified | 2006-12-29 |
| File Created | 2006-12-29 |