Inverse Probability Weights for Quasicontinuous Ordinal Exposures With a Binary Outcome: Method Comparison and Case Study

Inverse probability weighting (IPW), a well-established method of controlling for confounding in observational studies with binary exposures, has been extended to analyses with continuous exposures. Methods developed for continuous exposures may not apply when the exposure is quasicontinuous because of irregular exposure distributions that violate key assumptions. We used simulations and cluster-randomized clinical trial data to assess 4 approaches developed for continuous exposures-ordinary least squares (OLS), covariate balancing generalized propensity scores (CBGPS), nonparametric covariate balancing generalized propensity scores (npCBGPS), and quantile binning (QB)-and a novel method, a cumulative probability model (CPM), in quasicontinuous exposure settings. We compared IPW stability, covariate balance, bias, mean squared error, and standard error estimation across 3,000 simulations with 6 different quasicontinuous exposures, varying in skewness and granularity. In general, CBGPS and npCBGPS resulted in excellent covariate balance, and npCBGPS was the least biased but the most variable. The QB and CPM approaches had the lowest mean squared error, particularly with marginally skewed exposures. We then successfully applied the IPW approaches, together with missing-data techniques, to assess how session attendance (out of a possible 15) in a partners-based clustered intervention among pregnant couples living with human immunodeficiency virus in Mozambique (2017-2022) influenced postpartum contraceptive uptake.

Automated summary

Inverse probability weighting (IPW) is a well-established method used in observational studies to control for confounding. This study extended the use of IPW to analyze continuous exposures, specifically in cases of quasicontinuous exposures. Different approaches were assessed and compared using simulations and cluster-randomized clinical trial data. The results showed that certain methods, such as covariate balancing generalized propensity scores (CBGPS) and nonparametric covariate balancing generalized propensity scores (npCBGPS), achieved excellent covariate balance and lowest bias, while quantile binning (QB) and cumulative probability model (CPM) had the lowest mean squared error. The IPW approaches were also successfully applied to assess the influence of session attendance on postpartum contraceptive uptake in a partners-based clustered intervention in Mozambique.