Chapter four - Causal Inference and Generalization in Field Settings

Summary

This chapter introduces the researchers to randomized and non-randomized designs that permit relatively strong causal inferences, particularly in field settings. It discusses the perspectives on the generalization of causal effects. The chapter considers some basic issues in inferring causality, initially drawing on work by Rubin and his associates in statistics and later drawing on work by Campbell and his associates in psychology. It also considers three classes of quasi-experimental designs, the regression discontinuity design, the interrupted time series design, and the nonequivalent control group design. The emphasis on designs for field research in the chapter contrasts sharply with standard practice in basic social psychology. Randomized experiments are typically considered to be the gold standard for causal inference. Some basic research in social psychology and personality now focuses on areas such as the influence of culture, major life stressors, religion, intimate relationships, and evolution of social behavior.