Why match? Investigating matched case-control study designs with causal effect estimation

Abstract

Matched case-control study designs are commonly implemented in the field of public health. While matching is intended to eliminate confounding, the main potential benefit of matching in case-control studies is a gain in efficiency. Methods for analyzing matched case-control studies have focused on utilizing conditional logistic regression models that provide conditional and not causal estimates of the odds ratio. This article investigates the use of case-control weighted targeted maximum likelihood estimation to obtain marginal causal effects in matched case-control study designs. We compare the use of case-control weighted targeted maximum likelihood estimation in matched and unmatched designs in an effort to explore which design yields the most information about the marginal causal effect. The procedures require knowledge of certain prevalence probabilities and were previously described by van der Laan (2008). In many practical situations where a causal effect is the parameter of interest, researchers may be better served using an unmatched design.

Figure 1:

Simulated Covariates

Figure 2:

Simulated Covariates: Probabilities. Z represents the remaining eight non-matching covariates.

Figure 3:

Simulation 1 – Bias for 1:1 Matching. CCD I is CCW T-MLE for Case-Control Design I, CCD II is CCW T-MLE for Case-Control Design II with q̄₀(M) weighting, and CCD II (w) is CCW T-MLE for Case-Control Design II with (1 – q₀) weighting.

Figure 4:

Simulation 1 – Bias for 1:2 Matching. CCD I is CCW T-MLE for Case-Control Design I, CCD II is CCW T-MLE for Case-Control Design II with q̄₀(M) weighting, and CCD II (w) is CCW T-MLE for Case-Control Design II with (1 – q₀) weighting.

Figure 5:

Simulation 2 – Bias. CCD I is CCW T-MLE for Case-Control Design I and CCD II is CCW T-MLE for Case-Control Design II.