Statistical Approaches for Estimating Sex-Specific Effects in Endocrine Disruptors Research

Abstract

Background: When a biologic mechanism of interest is anticipated to operate differentially according to sex, as is often the case in endocrine disruptors research, investigators routinely estimate sex-specific associations. Less attention has been given to potential sexual heterogeneity of confounder associations with outcomes. When relationships of covariates with outcomes differ according to sex, commonly applied statistical approaches for estimating sex-specific endocrine disruptor effects may produce divergent estimates.

Objectives: We discuss underlying assumptions and evaluate the performance of two traditional approaches for estimating sex-specific effects, stratification and product terms, and introduce a simple modeling alternative: an augmented product term approach.

Methods: We describe the impact of assumptions regarding sexual heterogeneity of confounder relationships on estimates of sex-specific effects of the exposure of interest for three approaches: stratification, traditional product terms, and augmented product terms. Using simulated and applied examples, we demonstrate properties of each approach under a range of scenarios.

Results: In simulations, sex-specific exposure effects estimated using the traditional product term approach were biased when confounders had sex-dependent associations with the outcome. Sex-specific estimates from stratification and the augmented product term approach were unbiased but less precise. In the applied example, the three approaches yielded similar estimates, but resulted in some meaningful differences in conclusions based on statistical significance.

Conclusions: Investigators should consider sexual heterogeneity of confounder associations when choosing an analytic approach to estimate sex-specific effects of endocrine disruptors on health. In the presence of sex-dependent confounding, our augmented product term approach may be advantageous over stratification when there is prior knowledge available to fit reduced models or when investigators seek an automated test for effect measure modification. https://doi.org/10.1289/EHP334.

Figure 1.

Causal diagrams for relationships between exposure ($X$), outcome ($Y$), a measured covariate ($Z$), and sex ($S$) in the overall population (A), for $S=0$ (B), and for $S=1$ (C).