THE ANALYSIS OF STRATIFIED MULTIPLE RESPONSES

• Main Authors: Ivy Liu, Thomas Suesse
• Other Authors: The Pennsylvania State University CiteSeerX Archives
• Format: Text
• Language: English
• Published: 2007
• Subjects: Greenland
• Online Access: http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.630.2905; http://www.mcs.vuw.ac.nz/research/publications/reports/mscs/mscs07-05.pdf

Surveys often contain qualitative variables for which respondents may select any number of the outcome categories. For instance, for the question “What type of contraception have you used? ” with possible responses (oral, condom, lubricated condom, spermicide, and di-aphragm), respondents would be instructed to select as many of the outcomes that apply. This situation is known as multiple responses. When the data includes stratification variables, we discuss two approaches: (1) the model-based approach which uses logit models directly applying the generalized estimating equations (GEE) method (Liang and Zeger, 1986); and (2) the non-model-based approach which extends the generalized Mantel-Haenszel type es-timators (Greenland, 1989) to make inferences across multiple responses. These approaches can also be used for data with dependent observations across strata. Key words: bootstrap method, dually consistent, generalized estimating equations, gener-alized Mantel-Haenszel estimator, multiple responses; odds ratio. 1 1