|
Activity Number:
|
341
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods
|
| Abstract - #308857 |
|
Title:
|
Nonresponse Adjustment for Multipurpose Surveys
|
|
Author(s):
|
Hee-Choon Shin*+
|
|
Companies:
|
NORC at the University of Chicago
|
|
Address:
|
2232 University Dr, Naperville, IL, 60565,
|
|
Keywords:
|
Non-response Adjustment ; Multi-purpose Survey ; Weighting
|
|
Abstract:
|
The most common method of adjustment for unit non-response is weighting, where respondents and non-respondents are classified into adjustment cells based on some covariates known for all units in the sample, and a nonresponse adjustment factor is computed for all responding cases in each cell proportional to the inverse of the response rate in the cell. All the methods for non-response adjustment were developed for a single response or dependent variable. For example, the common predictive mean or response propensity stratification methods for constructing adjustment cells are based on a single outcome variable. We will describe a method for non-response adjustment for multi-purpose surveys in which there are hundreds of survey items.
|
