|
Activity Number:
|
163
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 13, 2002 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Survey Research Methods*
|
| Abstract - #300285 |
|
Title:
|
Some Uses of Latent Class Analysis in Survey Quality Evaluations
|
|
Author(s):
|
Paul Biemer*+
|
|
Affiliation(s):
|
RTI International
|
|
Address:
|
53A-1, P.O. Box 12194, Research Triangle Park, North Carolina, 27709-2194,
|
|
Keywords:
|
|
|
Abstract:
|
This paper describes and illustrates how latent class analysis (LCA) can be used to estimate the measurement bias and variance in survey estimates and then trace the sources of the error to specific questions on the questionnaire. The emphasis of the paper is on actual applications of the methodology rather than statistical theory. In that sense, the paper will provide the theoretical framework for LCA and Markov LCA as well as the models used in each illustration in both mathematical terms as well as in non-mathematical conceptual terms in order to appeal to the widest audience. The issues that arise in applying LCA will be introduced via a number of examples and illustrations from the author's own work. The goal of the paper is to show the usefulness of LCA for detecting problems in the design of survey questionnaires and to encourage greater use of this powerful statistical technique in the survey methods literature.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2002 program |
