Sankhya: The Indian Journal of Statistics

2007, Volume 69, Pt. 3, 379--404

Modelling Association Among Bivariate Exposures In Matched Case-Control Studies

Samiran Sinha, Texas A&M University, College Station, USA
Bhramar Mukherjee, University of Michigan, Ann Arbor, USA
Malay Ghosh, University of Florida, Gainesville, USA

SUMMARY. The paper considers the problem of modelling association between two exposure variables in a matched case-control study, where both the exposures may be partially missing. The exposure variables could all be categorical or continuous or could be a mixed set of some categorical and some continuous variables. Association models for the missing exposure variables using the completely observed covariates and disease status are proposed for each of the three scenarios. The models account for varying stratum heterogeneity in different matched sets. Three real data examples accompany the proposed models. The examples as well as a small scale simulation study indicate that in presence of missingness and association, modelling the association between the exposures rather than ignoring it, often leads to better estimates of the relative risk parameters with smaller standard errors. Estimation of the model parameters is carried out in a Bayesian framework and the estimates are compared with classical conditional logistic regression estimates.

AMS (2000) subject classification. Primary 62F10, 62F15, 62H12.

Key words and phrases. Association model, benign breast disease, colon cancer, conditional likelihood, endometrial cancer, matched designs, measurement errors, missing at random.

Full paper (PDF)