According to Stuart (2010), which of the following statements about observational study designs for causal inference are typically true? Choose all that apply. Including propensity score estimates as a predictor in a regression model on outcomes can help resolve imbalance between treatment and control groups for covariates used in the propensity score model Standard diagnostic tools for binary prediction or classification models (e.g. logistic regression or classification trees) are similarly used in evaluating propensity score estimates When conditional ignorability holds given the observed covariates, then the treatment assignment will also be ignorable conditioned on the propensity scores Overfitting in propensity score estimation can achieve more efficient estimates of treatment effects than using propensity score estimates that are closer to the true propensities Unlike full matching, subclassification, and weighting methods, nearest neighbor matching does not necessarily use all individuals within the area of overlap