Thursday, October 28, 2021
11:00am Eastern Time

Tengfei Li
Georgetown University

Causal Inference Methods for Measures of Health Disparities

There is increased interest in the evaluation of health disparities between different socioeconomic groups using data from observational studies. However, in the absence of randomization, the results and conclusions may be limited to associations rather than causal effects. The causal inference framework allows us to estimate causal measures for such situations. We present inverse probability weighting (IPW) and doubly robust (DR) estimators for the marginal means of the distributions of the potential outcomes for multiple socioeconomic groups using generalized propensity scores. We estimate the variance of the vector of IPW and DR estimators for the marginal means by using an M-estimation approach. The variances of the estimators for causal measures of health disparities are subsequently estimated using the multivariate delta method. In simulation studies, the new methods provide coverage probabilities that are close to the nominal level when used to construct 95% confidence intervals for the causal measures of health disparities.

Keywords: health disparities, inverse probability weighting estimator, doubly robust estimator, generalized propensity score, M-estimation.