A Semiparametric Odds Ratio Model for Measuring Association
We propose a semiparametric odds ratio model to measure the association between two variables taking discrete values, continuous values, or a mixture of both. Methods for estimation and inference with varying degrees of robustness to model assumptions are studied. Semiparametric efficient estimation and inference procedures are also considered. The estimation methods are compared in a simulation study and applied to the study of associations among genital tract bacterial counts in HIV infected women.
Document Type: Research Article
Affiliations: Division of Epidemiology and Biostatistics, School of Public Health, University of Illinois at Chicago, Chicago, Illinois 60612, U.S.A.
Publication date: June 1, 2007