Objective: To evaluate the statistical property of the estimators on exposure effect and value of propensity score methods in practical use.
Methods: Simulation data, propensity score methods (PSM) were conducted to assess bias and efficiency, under both with/without model misspecification conditions.
Results: Under model misspecification conditions, propensity score methods had better robustness than model based methods.
Conclusion: For large and complicated data, propensity score methods had more flexibility in practical use than model based methods.