|
Activity Number:
|
359
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 14, 2002 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Survey Research Methods*
|
| Abstract - #301670 |
|
Title:
|
Use of a Permanent Random Number Technique to Avoid Response Burden in Repeated Surveys
|
|
Author(s):
|
Darryl Creel*+ and Donsig Jang and Nancy Clusen and Thomas Williams
|
|
Affiliation(s):
|
Mathematica Policy Research, Inc. and Mathematica Policy Research, Inc. and Mathematica Policy Research, Inc. and TRICARE Management Activity
|
|
Address:
|
600 Maryland Avenue, SW Suite 550, Washington, District of Columbia, 20024, United States of America
|
|
Keywords:
|
Health Care Survey of Department of Defense Beneficiaries (HCSDB) ; Logistic Regression ; Permanent Random Number Technique ; Quarterly Survey ; Response Propensity
|
|
Abstract:
|
The increasing use of healthcare surveys has been accompanied by a steady drop in cooperation rates within sampled populations. This trend compromises the usefulness of these data and indicates methods to reduce survey burden. In regularly repeated surveys, some people may be selected more than once in a relatively short time span. It is believed that they would be less likely to respond to the survey if they are sampled more than once in the same survey. We investigated this conjecture using a logistic regression for beneficiaries who were selected more than once during 1997--1999 Health Care Survey of Department of Defense Beneficiaries (HCSDB). To avoid selecting the same units in a relatively short time period, a permanent random number technique is proposed.
|
