Polytomous logistic model for matched pairs case-control design: Studies with covariates

S. S. Ganguly, U. Naik-Nimbalkar

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Pair-wise matched case-control design is commonly used in epidemiological analysis for estimating odds ratios. In the most simplest situation, each subject is classified according to a binary outcome and the factor of interest being a two-level factor. Binary logistic models have been found to be very useful for studying such relationship. In our earlier studies we have shown that polytomous logistic model can be used for estimating odds ratios when the exposure of prime interest assumes multiple levels. In this paper, using the above model, we estimate the odds ratios for the possible levels of risk factor of interest adjusting for covariates which were not included in the matching process. An illustrative example is presented and discussed.

Original languageEnglish
Pages (from-to)455-464
Number of pages10
JournalJournal of Applied Statistics
Volume19
Issue number4
DOIs
Publication statusPublished - Jan 1 1992

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Statistics and Probability

Fingerprint Dive into the research topics of 'Polytomous logistic model for matched pairs case-control design: Studies with covariates'. Together they form a unique fingerprint.

  • Cite this