This study aims to overview some research design and analysis strategies for examining the effectiveness of educational polices and programs under the potential outcomes framework, also known as Rubin's causal model (Holland, 1986). Required assumptions and strengths/weaknesses of each design and analysis strategy were discussed in estimating causal effects, especially focusing on propensity score matching approaches, regression-discontinuity designs, and instrumental variables methods. Exemplary studies that actually implemented such research methods to estimate causal effects were also discussed for better understanding of the underlying conditions. This study highlights that decisions on which design and analysis methods might be preferable in a certain situation should be made based on an array of factors, including careful consideration of the target populations, the treatment effects of interest, the treatment assignment mechanism, and imbalance and lack of overlap in key pre-treatment variables. This study will provide guidelines for applied educational researchers to conduct impact studies in educational research.