Sample Design

The 1998 Motor Vehicle Occupant Safety Survey, like both the baseline Motor Vehicle Occupant Safety Survey in 1994 and its follow-up survey of 1996, 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 each of the two survey instruments (one focusing on safety belts and the other on car seats, with a common core of questions relating to personal characteristics and driving behaviors), a national probability sample was developed. Each sample was composed of approximately 4,000 persons age 16 and older, including oversamples of persons age 16-39. Since the sampling procedures and data collection methodology for the two samples were identical, procedures described in this report for one sample apply to the other as well.

The procedure for developing a population-based sample for this telephone survey involved four stages. The first stage sample involved 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 within the geographically stratified first stage sample design. The third stage in the sampling procedure was to conduct 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 population sample of the eligible population. These procedures yielded national estimates of the target population, within specified limits of expected sampling variability, from which valid generalizations can be made to the general public.


Sample Construction

Most of the statistical formulas associated with sampling theories are based upon the assumption of simple random sampling. Specifically, the statistical formulas for specifying the sampling precision (estimates of sampling variance), given particular sample sizes, are premised on simple random sampling. Unfortunately, random sampling requires that all of the elements in the population have an equal chance of being selected. 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 an approximation of the actual population and survey samples are generated by a process closely resembling true random sampling.

The survey sample was based on a modified stratified random digit dialing method, using an area probability/RDD sample rather than a single-stage/RDD sample. There are several important advantages to using an area probability base: (1) it draws the sample proportionate to the geographic distribution of the target population rather than the geographic distribution of telephone households, which is vital to constructing unbiased population estimates from telephone surveys; (2) it allows greater geographic stratification of the sample to control for known geographic differences in non-response rates; and (3) it facilitates the use of Census estimates of population characteristics to weight the completed sample to correct for other forms of sampling bias. Moreover, the precision of sample estimates is generally improved by stratification.

Hence, as specified for the study design for the survey, the adult household population of the United States was stratified by the ten NHTSA regions. The estimated distribution of the population by stratum was calculated on the basis of the Bureau of the Census, Resident Population of the United States, Regions and States by Selected Age Groups and Sex: April 1, 1990 Census and July 1, 1995 to July 1, 2050 Estimates (release date, February 1998). At the time of the survey, these were the most recent projections of the distribution of adult population by state. Based on these Census data on the geographic distribution of the target population, the total sample was proportionately allocated by stratum. The geographic allocation of the cross-sectional sample for the survey is presented in Table 1.



TABLE 1
Population Aged 16 and Older by NHTSA Region:
February, 1998

Region State Population
207,594,256
Cross-Section
Proportion
100.00%
Cross-Section
Sample
(3,000)
Region I CT, ME, MA, NH, RI, VT 10,565,351 5.09 153
Region II NJ, NY 20,321,261 9.79 294
Region III DE, DC, MD, PA, VA, WV 21,443,106 10.33 310
Region IV AL, FL, GA, KY, MS, NC, SC, TN 39,268,081 18.92 567
Region V IL, IN, MI, MN, OH, WS 37,650,887 18.14 544
Region VI AR, LA, NM, OK, TX 23,792,984 11.46 344
Region VII IA, KS, MO, NE 9,780,660 4.71 141
Region VIII CO, MT, ND, SD, UT, WY 6,771,875 3.26 98
Region IX AZ, CA, HI, NV 29,589,196 14.25 428
Region X AK, ID, OR, WA 8,410,855 4.05 122
Source:   Resident Population of the United States, Regions and States by Selected Age
Groups and Sex: April 1, 1990 Census and July 1, 1995 to July 1, 2050
Estimates
, U.S. Bureau of the Census, (release date, February 1998).

Once the sample had been geographically stratified with sample allocation proportionate to population distribution, a sample of assigned telephone banks were randomly selected from an enumeration of the Working Residential Hundreds Blocks of 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 3 or more residential listings. (Exchanges with one or two listings were excluded because in most cases such listings represent errors in the published listings).

The use of residential listings to identify working residential exchanges is generally described as "listed assisted" or "truncated" RDD sampling. In a series of empirical studies, Brick, et. al. demonstrated that only about four percent of all telephone households are excluded in national samples using this method. In addition, these studies indicate that the differences between covered and uncovered samples are trivial in most instances. The principal advantage of "list assisted" sampling is that an equal probability systematic sample of telephone numbers can be selected under this procedure and the variances of estimates from the list-assisted sample are usually lower than those from a clustered design like the Mitovsky-Waksberg RDD method.

In the third stage sample, a two digit number was randomly generated by computer for each Working Residential Hundreds Block selected in the second stage sample. This third stage sampling process is the random digit dialing (RDD) component. Every telephone number within the Hundreds Block has an equal probability of selection, regardless of whether it is listed or unlisted.

The third stage RDD sample of telephone numbers was then dialed by SRBI interviewers to determine which were currently working residential household phone 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 adult in the household, language barriers) were also immediately replaced. Non-answering numbers were not replaced until the research protocol (in this study, a five call protocol) was exceeded.


Screening to Determine Household Eligibility

The sample construction process yielded a population-based, random-digit dialing sample of telephone numbers. The systematic dialing of those numbers to obtain a residential contact yielded a random sample of telephone households. The next step was to select eligible households within the total sample of working numbers.

An adult respondent at each number drawn into the sampling frame was contacted about the composition of the household. Telephone numbers that yielded non-residential contacts such as businesses, churches, and college dormitories, were screened out. Only households, i.e., residences at which any number of related individuals or no more than five unrelated persons living together, were eligible for inclusion in the sample. This minimal screening was only to ascertain that the sample of telephone numbers reached by interviewers are residential households.


Selection of Respondent Within Household

The multi-stage sampling process described in the previous sections yielded a random national sample of households with telephones, drawn proportionate to the population distribution. The final stage required the selection of one respondent per household for the interview.

A systematic selection procedure was used to select one designated respondent for each household sampled. The "most recent/next birthday method" was used for within household selection among multiple eligibles. The Within Household Selection Procedure is presented in Figure 1. The CATI system alternated the "most recent" and "next" birthday specification for the selected respondent to avoid a temporal bias for birthdays before (or after) the field period.



FIGURE 1
Within Household Selection Procedure:
Adult Cross-Section


TIME START: _____________ TIME END: _____________

DATE: _____________ BATCH #:____________ CATI RESP. #: ______________

SAMPLE POINT #: ___ ___ ___ GENDER OF RESP.: MALE [ ] FEMALE [ ]

RESP PHONE NUMBER: _________________________________________________________

RESP POSITION IN HOUSEHOLD: ________________________________________________

INTERVIEWER NAME: __________________________________________________________

THIS INTERVIEW IS A: COMPLETE [ ] CALLBACK FOR COMPLETION [ ]

TERMINATE AT Q._____ [ ]

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

INTRODUCTION TO BE ADMINISTERED TO ANY ADULT HOUSEHOLD MEMBER:
Hello, I'm calling for the U.S. Department of Transportation. We are conducting a study of Americans' driving habits and their attitudes about current driving laws. The interview is completely confidential.
C1.

    In order to select just one person to interview, could I speak to the person in your household, age 16 and older, who has had the most recent/next birthday?
    Respondent is that person [CONTINUE WITH CATI AND ENTER Q.1 AS C1]....................1
    Other respondent came to phone [CONTINUE WITH CATI AND ENTER Q.1 AS C1]...................2
    Respondent is not available
      [ARRANGE CALLBACK AND RECORD IT, ALONG WITH THE
      RESPONDENT'S FIRST NAME OR HH POSITION, ON THE SAMPLE SHEET.
      ATTACH THIS SHEET TO SAMPLE AFTER FILLING OUT APPLICABLE
      RESPONDENT INFO AT THE TOP. WHEN THE NEXT INTERVIEWER
      REACHES THIS PERSON, THEY WILL ENTER Q.1 AS C1]...................3



Young Adult Oversample

The survey design specified an oversample of 16-39 year olds in the achieved sample in order to permit more detailed analysis of this subset of the population. A random sample of all persons age 16 and over in an RDD sample of 4,000 households yields too few individuals in this range to allow very close examination. Therefore, to increase the subsample sizes of the 16-39 year olds, within a projectable national sample, an independent national sample was conducted of that population. The allocation of sample by region for the young adult oversample is proportional to the regional distribution of that population. The household selection procedures through RDD is the same for the oversample as for the national cross-sectional sample.

The screening criteria for the oversample were different from the simple cross-section in that households were screened for persons age 16 to 39. This systematic screening of a national probability sample of households for a subset of the total household population should yield a random sample of that population. As in the case of the simple cross-sectional sample, if there was only one eligible respondent in the household then he or she was selected. If there were more than one eligible respondent, then the "most recent/next birthday" method of selection was used. The oversample screener script is presented in Figure 2.



FIGURE 2
Within Household Selection Procedure:
Young Adult Oversample


TIME START: _____________ TIME END: _____________

DATE: _____________ BATCH #:____________ CATI RESP. #: ______________

SAMPLE POINT #: ___ ___ ___ GENDER OF RESP.: MALE [ ] FEMALE [ ]

RESP PHONE NUMBER: ___________________________________________________

RESP POSITION IN HOUSEHOLD: ________________________________________________

INTERVIEWER NAME: __________________________________________________________

THIS INTERVIEW IS A: COMPLETE [ ] CALLBACK FOR COMPLETION [ ]

TERMINATE AT Q._____ [ ]

- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -

INTRODUCTION TO BE ADMINISTERED TO ANY ADULT HOUSEHOLD MEMBER: Hello, I'm calling for the U.S. Department of Transportation. We are conducting a study of Americans' driving habits and their attitudes about current driving laws. The interview is completely confidential.
D1.  Is there anyone age 16 to 39 years old living in your household?

    |---------------- Yes [ASK Q.D2].................1
    |               No [SCREEN OUT - D1 AGE].........2
    |

    D2.  Could I speak to the person in your household, age 16 to 39, who has had the most recent/next birthday?

    Respondent is that person [CONTINUE WITH CATI AND ENTER Q.1 AS D2]................1

    Other respondent came to phone [ CONTINUE WITH CATI AND ENTER Q.1 AS D2]......2

    Respondent is not available [ARRANGE CALLBACK AND RECORD IT, ALONG WITH
    THE RESPONDENT'S FIRST NAME OR HH POSITION, ON THE SAMPLE SHEET.
    ATTACH THIS SHEET TO SAMPLE AFTER FILLING OUT APPLICABLE RESPONDENT
    INFO AT THE TOP. WHEN THE NEXT INTERVIEWER REACHES THIS PERSON,
    THEY WILL ENTER Q.1 AS D2].......................3



Table 2 presents the national population figures and projected sample distribution by age and sex for the total sample of 4,000 respondents, including the cross-sectional sample of 3,000 respondents and the oversample of 1,000 persons age 16-39.



TABLE 2
Population and Expected Sample Distribution
*

Population
Sample
Total
Population
(thousands)
% Cross-
Sectional
Sample
Young
Adult
Sample
Total
Total (16+) 207,145 100 3,000 1,000 4,000


Males (16+)


100,049


48.3


1,449


505


1,954
16-20 9,890 4.8 143 104 247
21-29 16,481 8.0 239 174 413
30-39 21,431 10.4 310 226 536
40-64 38,153 18.4 553 - 553
65+ 14,093 6.8 204 - 204


Females(16+)


107,095


51.7


1551


495


2,046
16-20 9,293 4.5 135 98 233
21-29 16,068 7.8 233 170 402
30-39 21,537 10.4 312 227 539
40-64 40,083 19.4 581 - 581
65+ 20,113 9.7 291 - 291
*Source:    Population Projections of the United States by Age, Sex, Race and Hispanic Origin: 1995 to 2050. Bureau of the Census. Middle Series estimates for February, 1998.


Initial Contact

Initial telephone contact was attempted during the hours of the day and days of the week which have the greatest probability of respondent contact. The primary interviewing period was from 5:30 p.m. to 10:00 p.m. on weekdays, from 9:00 a.m. to 10:00 p.m. on Saturdays, and from 10:00 a.m. to 10:00 p.m. on Sundays (all times are local time). Since interviewing was conducted across time zones, the interviewing shift lasted until 1:00 a.m. Eastern Time (10:00 p.m. Pacific Time).

If the interview was not conducted at the time of 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 elicit a respondent contact, the fifth contact was attempted on a weekday.

Interviewers attempted a minimum of five calls to each telephone number. When the household was reached, the interviewer asked to speak to an adult to screen the household for eligibility and to determine the designated respondent. When the designated 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 not the designated respondent(s), interviewers probed for appropriate callback times and attempted to set up an appointment.


Spanish Language Interviews

Spanish language versions of the two survey instruments were developed in order to eliminate language barriers for a small proportion of the U.S. adult population. If the interviewer encountered a language barrier at the telephone number, 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 in which a language barrier (Spanish) was encountered were assigned to a Spanish-speaking interviewer. These bilingual interviewers recontacted the Spanish-speaking households to screen for eligibility and conduct interviews with eligible respondents.


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 terminates were reported on a daily basis and the Project Director and Operations Manager reviewed them after each shift to see if anything unusual was occurring. Second, after enough time had passed to see a large enough sample of refusals and terminations, the Project Director and his staff developed a refusal conversion script. Third, the refusal conversion effort was fielded with reinterview attempts scheduled about a week after the initial refusal. Fourth, the Project Director and Operations Manager received the outcomes of the refusal conversion efforts on a daily basis. Minor revisions of the script and the procedures were made, as needed. The final refusal conversion script is shown in Figure 3, on the following two pages.




FIGURE 3
Refusal Conversion Script


Hello, my name is __________________________________. I am a field supervisor with SRBI, a national research organization in New York. I believe that someone in your household may have been contacted by one of our interviewers concerning a public policy study that we are conducting for the U.S. Department of Transportation in Washington, D.C.

    Yes, respondent...........1
    Yes, other................2
    No, don't recall..........3

    1. In order to assess the effectiveness of current traffic laws, the U.S. Department of Transportation is conducting a study of Americans' attitudes about current driving laws. It is a public opinion study that will help the government to consider traffic laws in light of what the public really wants and does. It only takes about fifteen minutes and it's strictly confidential.

      Willing to proceed........1 GO TO SELECTION GRID
      Refuses...................2

    2. I understand. My job as a field supervisor is to find out if there are any problems with our surveys or interviewers that are discouraging people from participating. Could you tell me if we have done something wrong or is there something about the interview that concerns you?

IF: ANSWER:
I don't do surveys.
I understand, but this is the first survey to really examine whether our traffic laws are realistic and appropriate in terms of what people really want and really do. The results will be presented to Congress and may affect laws in your state. It is really important.
IF ANSWER:
I don't have time.
It doesn't take very long and we can schedule it at a time convenient to you. We need to represent the opinions of busy people like you, as well as people who have more time, if we are to present an accurate picture to Congress of what the public thinks and wants.
IF: ANSWER:
I don't know if you are who you say you are.
I can give you our 800 number to call and confirm the authenticity of the study.
IF: ANSWER:
I don't know how the results will be used.
The Department of Transportation has been charged by the Congress to report to them about public opinion and behavior related to traffic laws, in order to assist them in determining whether certain laws should be changed or not. That's why we need to talk to you.
IF: ANSWER:
I don't drive.
Then the interview should only take a few minutes. Even if you don't drive, we need to get your opinion about some traffic laws that may affect you as a pedestrian. We also need a little background about non-drivers, but it won't take long at all.
IF: ANSWER:
Don't know enough.
This is an opinion survey about driving, traffic safety and traffic laws based on your experience. We need to talk to all kinds of people to get a true picture of what ordinary Americans think, not just what "experts" say.
IF: ANSWER:
I don't want the government to know about me/ what I do.
The interview is strictly confidential. Your telephone number was selected at random. As soon as we complete the interview and verify it, we destroy the phone number. No one will ever know who you are. We do this so that you can be comfortable in telling us what you really think, not what you think the government wants to hear.
IF: ANSWER:
It's a bad time.
We can schedule a callback for a time that would be good for you.

    Date _____________ Time _____________________

IF STILL HESITANT SAY:

    It is really important that we represent the views and experience of people like yourself so that the findings will be fair and accurate. You don't often get a chance to participate in studies that may affect the laws in your community. It's really important and we really want to represent your household in the study. If now is a bad time, we can schedule the interview during the day, in the evening, or on the weekend whenever is better for you.

    (IF SUGGESTS A TIME MORE THAN TWO WEEKS HENCE:
    We are supposed to finish the study by the end of November. Could we find some time this week (or next) to do the interview?)

    Date _____________ Time _____________________

IF AGREEABLE, GO TO THE SELECTION GRID.
IF STILL REFUSES, THANK AND COMPLETE.




TOP | NEXT | PREVIOUS | TABLE OF CONTENTS |