Field Outcomes

Survey data collection by the Federal government requires prior approval by the Office of Management and Budget (OMB). Before submitting the formal request for data collection to OMB, NHTSA published a Notice in the Federal Register soliciting comments on the information collection. The Notice appeared in the Federal Register, 67:40, pages 9353-9354, February 28, 2002. No comments were received in response to the Notice. NHTSA then submitted the request for data collection to OMB. OMB approved the information collection on December 10, 2002, assigning it the OMB number 2127-0618 with an expiration date of December 31, 2003.

The field interviewing for the study commenced on January 8, 2003, following training of the field interviewers, and was completed on March 30, 2003. This was approximately the same length of field period as the 2000 Motor Vehicle Occupant Safety Survey (November 8, 2000 to January 21, 2001), the 1998 Motor Vehicle Occupant Safety Survey (November 8, 1998 to January 12, 1999), the 1996 Motor Vehicle Occupant Safety Survey (November 4, 1996 to January 5, 1997) and the 1994 Motor Vehicle Occupant Safety Survey (October 5, 1994 to December 11, 1994). However, the field period for the 2003 survey was moved to January to March in order to permit us to report results in the same calendar year as the data were collected. There was no reason to expect that the survey results would be affected by this change. Case status at the end of the field period was reported using the categories defined in Figure 4.

A total of 6180 interviews were conducted using Version 1, including 4677 for the cross-section and 1503 for the young adult over-sample. The average interview length for Version 1 was 21.7 minutes for the cross-section and 19.7 minutes for the over-sample. A total of 6197 interviews were completed using Version 2, including 4698 for the cross-section and 1499 for the young adult over-sample. The average interview length for Version 2 was 17.2 minutes for the cross-section and 17.8 minutes for the over-sample.

FIGURE 4
Sample Disposition Categories
NIS/DIS/Change # The number was not in service, disconnected, or no longer an active number.
Non-residential The number yielded a contact with a business, government agency, pay telephone, or other identifiable non-residential unit.
Computer/Fax

The number yielded an electronic tone indicating a fax machine or data line. A handful of other non-household numbers are included in this category.

Line problems

These represent dialing attempts that did not result in other standard outcomes and may be bad area codes, or other transient or permanent connection problems.

Probably unassigned

No answers, exclusively, were encountered on every contact over a period of several weeks until the study protocol (10 attempts) was reached.

Non-contact (max)

Answering machines or busy signals, as well as no answers, were encountered on all contact attempts until the study protocol (10 attempts) was reached.

No answer/busy

No household contact ever achieved, but less than 10 attempts. Ring, no answer or repeated busy signal on last attempt.

Answering machine

No household contact ever achieved, but less than 10 attempts. An answering machine was reached at the telephone number.

Language barrier

The interview could not be completed because of language barriers other than Spanish (which was treated as Spanish callback).

Health/Deaf The designated respondent was unable to participate due to health or deafness.
Away for duration The designated respondent was out of the area for the entire field period.
Screen-Outs Households whose eligible participants did not meet the 16-39 age requirement in the over-sample version.
Quota Outs Households whose eligible participants had met the gender by region quotas.
Callback

Contact was made with the household, but not necessarily the designated respondent

Refusal -- Initial Someone in the household refused before selection of a designated respondent.
Refusal -- Second Either an extremely strong initial refusal or a second refusal was encountered during refusal conversion, but before selection of a designated respondent.
Qualified Callback The designated respondent had neither completed, nor refused an interview.
Refusal – Qualified The designated respondent refused to participate in the survey.
Terminate A respondent began the interview but refused to finish.
Complete An interview was completed with the designated respondent.


For survey Version 1 Seat Belt Usage Issues, a total of 53,366 randomly selected telephone numbers were sampled within a geographically stratified national sampling frame for both sample components (the cross-section age 16 and older and the over-sample of persons age 16-39):

At the close of the field period, only 1,675 cases (3%) were in callback status and an additional 1,460 cases (3%) were no answers or answering machines with less than 10 attempts.

The participation rate represents one of the most critical measures of potential sample bias because it indicates the degree of self-selection by potential respondents into or out of the survey. The participation rate is calculated as the number of completed interviews (including respondents who screen-out or quota out as ineligible) divided by the combined total number of completed interviews, terminated interviews, and refusals to interview. The participation rate for Version 1 is based on the following elements:

Based on the standard calculations of participation rate, the participation rate for Version 1 was 79.3%. The response rate3 (40.0%) was lower because it included all presumed eligible households in the denominator. Response rate was a measure of sample coverage. The Final Summary Disposition of the Version 1 sample is given in Table 3. The table includes breakouts for each survey component (national cross-section and the age 16-39 over-sample).

TABLE 3
Sample Disposition - Version 1, Seat Belt Usage Issues: 2003
Version 1, 2003
CROSS-SECTION
OVER-SAMPLE
TOTAL
T TOTAL
29544
23822
53366
   
   
   
 
A1 NON-ELIGIBLE HOUSEHOLD
13878
11027
24905
A NIS/DIS/Change#/Intercepts
9648
7664
17312
A Non-residential #
2367
1792
4159
A Computer/Fax tone
1672
1405
3077
A Line problem
191
166
357
   
  
 
 
B1 UNKNOWN ELIGIBLE HOUSEHOLD
3397
2588
5985
B Probable unassigned number (10 attempts)
1786
1487
3273
B Non-contact (10 attempts)
710
542
1252
B No answer/Busy (less than max attempts)
569
318
887
B Answering machine (less than max attempts)
332
241
573
     
  
  
  
C1 NOT ELIGIBLE REPONDENT
1134
5584
6718
C Language barrier
231
135
366
C Health/Deaf
344
93
437
C Respondent away for duration
49
35
84
C Screen-out (No aged 16-39)
0
5321
5321
C Quota-out (gender/region quota)
510
0
510
   
 
 
 
D1 UNKNOWN ELIGIBLE RESPONDENT
5699
2846
8545
D Callback (10 attempts)
3094
1678
4772
D Callback (less than max attempts)
773
241
1014
D Spanish Callback not screened
106
55
161
D Refusals Initial
693
295
988
D Refusals Second/Hard
1033
577
1610
      
  
 
 
E1 QUALIFIED NON-COMPLETE
759
274
1033
E Qualified callback
385
115
500
E Refusals Qualified
290
124
414
E Terminates
84
35
119
   
 
 
 
F COMPLETE
4677
1503
6180
F Total Completes
4677
1503
6180
   
 
 
  
A' ELIGIBLE HH=C+D+E+F/A+C+D+E+F
46.9%
48.1%
 
B' ESTIMATED QUALIFIED HH=B * A'
1594
1244
2838
C' ELIGIBLE RESPONDENTS=E+F/C+E+F
82.7%
24.1%
 
D' ESTIMATED ELIGIBLE RESPONDENTS=D * C'
4715
687
5402
   
 
 
  
  AAPOR RESPONSE RATE 3=F/(F+E+B'+D')
39.8%
40.5%
40.0%
   
 
  
  
  Participation Rate
71.2%
86.9%
79.3%


For survey Version 2 Child Safety Seat Issues, a total of 44,327 randomly selected telephone numbers were sampled within a geographically stratified national sampling frame for both sample components (the cross-section age 16 and older and the over-sample of persons age 16-39):

At the close of the field period, only 1,314 cases (3%) were in callback status and an additional 3,546 cases (8%) were no answers or answering machines with less than 10 attempts.

The participation rate for Version 2 is based on the following elements:

Based on the standard calculations of participation rate, the participation rate for Version 2 was 79.5 percent. The response4 rate (44.9%) was lower because it included all presumed eligible households in the denominator. Response rate was a measure of sample coverage. The Final Summary Disposition of the Version 2 sample is given in Table 4, on the next page. The table includes breakouts for each survey component (national cross-section and the age 16-39 over-sample).

TABLE 4
Sample Disposition - Version 2, Child Safety Seat Issues: 2003
Version 2, 2003 CROSS-SECTION OVER-SAMPLE TOTAL
T TOTAL
25643
18676
44319
   
 
 
 
A1 NON-ELIGIBLE HOUSEHOLD
11828
8960
20788
A NIS/DIS/Change#/Intercepts
8333
6260
14593
A Non-residential #
1921
1586
3507
A Computer/Fax tone
1489
1081
2570
A Line problem
85
33
118
   
 
 
 
B1 UNKNOWN ELIGIBLE HOUSEHOLD
4106
1744
5850
B Probable unassigned number (10 attempts)
215
859
1074
B Non-contact (10 attempts)
401
829
1230
B No answer/Busy (less than max attempts)
2432
39
2471
B Answering machine (less than max attempts)
1058
17
1075
   
 
 
 
C1 NOT ELIGIBLE REPONDENT
606
4056
4662
C Language barriers
194
107
301
C Health/Deaf
143
40
183
C Respondent away for duration
24
15
39
C Screen-out (No aged 16-39)
0
3894
3894
C Quota-out (gender/region quota)
245
0
245
   
 
 
 
D1 UNKNOWN ELIGIBLE RESPONDENT
3661
2185
5846
D Callback (10 attempts)
1590
1260
2850
D Callback (less than max attempts)
783
51
834
D Spanish Callback not screened
44
53
97
D Refusals - Initial
467
318
785
D Refusals Second/Hard
777
503
1280
   
 
 
 
E1 QUALIFIED NON-COMPLETE
744
232
976
E Qualified callback
311
72
383
E Refusals - Qualified
290
107
397
E Terminates
143
53
196
   
 
 
 
F COMPLETE
4698
1499
6197
F Total Completes
4698
1499
6197
   
 
 
 
A' ELIGIBLE HH=C+D+E+F/A+C+D+E+F
45.1%
47.1%
 
B' ESTIMATED QUALIFIED HH=B * A'
1851
821
2672
C' ELIGIBLE RESPONDENTS=E+F/C+E+F
90.0%
29.9%
 
D' ESTIMATED ELIGIBLE RESPONDENTS=
D * C'
3294
654
3948
   
 
 
 
  AAPOR RESPONSE RATE 3=F/(F+E+B'+D')
44.4%
46.8%
44.9%
   
   
  
  
  Participation Rate
74.7%
84.6%
79.5%


3Response Rate 3 (RR3) from the American Association for Public Opinion Research, Standard Definitions: Final Dispositions of Case Codes and Outcome Rates for Surveys, 2004, was used as the basis for this calculation.

4Response Rate 3 (RR3) from the American Association for Public Opinion Research’s Standard Definitions: Final Dispositions of Case Codes and Outcome Rates for Surveys, 2004, was used as the basis for this calculation.

Back
Top
Next
Table of Contents