Using ODA to Estimate Propensity-Weight-Adjusted Treatment Effects for Multi-Valued Treatments

Paul R. Yarnold, Ph.D., Fred B. Bryant, Ph.D., Ariel Linden, Dr.P.H.

Optimal Data Analysis, LLC, Loyola University Chicago, Linden Consulting Group, LLC

We demonstrate the use of optimal data analysis to obtain a hierarchically optimal classification tree-based propensity score model for an application with three (treatment) groups, and to assess outcome differences between treatment groups after weighting observations by propensity scores to reduce threats to causal inference.

View journal article

Leave a comment