|
Activity Number:
|
265
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Social Statistics Section
|
| Abstract - #304474 |
|
Title:
|
Nonresponse Bias Estimation in the 2008 Omnibus Household Survey
|
|
Author(s):
|
Promod Chandhok*+
|
|
Companies:
|
U.S. Department of Transportation
|
|
Address:
|
Bureau of Transportation Statistics/RITA, Office of Survey Programs, Washington, DC, 20590,
|
|
Keywords:
|
travel surveys ; nonresponse error ; response propensity ; call history ; early-responders ; late-responders
|
|
Abstract:
|
The 2008 Omnibus Household Survey was a random-digit-dial survey of slightly more than 1,000 non-institutionalized residents in telephone households in the U.S. Data were collected to monitor expectations of and satisfaction with the transportation system. As the response rate for the survey was approximately 53%, the Office of Management and Budget requires an assessment of the nonresponse (NR) bias for the survey. There are mainly four options for assessing the NR bias. The first is an intensive follow-up of nonrespondents. Cost considerations prohibited this option. The second option is external validation -- benchmarking against some other data, and this was done here. Another two approaches use information on the frame and survey operations. This paper discusses results from two methodologies--the response propensity approach and this the early-versus late-responders approach.
|
