This issue includes six articles that present logic, methods, and models for causal analyses of observational data, in particular those based on propensity score (PS) methods. The articles include a general introduction to propensity score analysis (PSA), uses of PSA in mediation studies, issues involved in choosing covariates, challenges that often arise in PSA applications, hierarchical data issues and models, and an application in an educational testing context. In this editorial I briefly summarize each article and make a few recommendations that relate to future applications in this field: the first pertains to how propensity score (PS) work could profit by connecting it with stronger forms of randomized experiments, not just simple randomization; the second to how and why graphical methods could be used to greater advantage in PSA studies; then why it might be helpful to reconsider the meaning of the term "treatments" in observational studies and why conventional usage might be modified; and finally, to the distinction between retrospective and prospective approaches to observational study design, noting the advantages, when feasible, of the latter approach.