This chapter provides an overview of methodological and practical issues in estimating causal relationships in labor economics. It discusses four identification strategies—control for confounding variables, fixed-effects and differences-in-differences, instrumental variables, and regression discontinuity—and five empirical examples: the effects of schooling, unions, immigration, military service, and class size. The chapter also covers data collection strategies, including secondary sources, primary data collection, and administrative data. It addresses measurement issues, such as measurement error models and the reliability of labor market data. The authors emphasize the importance of distinguishing between variables with causal effects, control variables, and outcome variables, and they discuss the challenges of generalizing findings from observational studies. The chapter highlights the growing use of quasi-experimental methods and the role of economic theory in causal modeling.This chapter provides an overview of methodological and practical issues in estimating causal relationships in labor economics. It discusses four identification strategies—control for confounding variables, fixed-effects and differences-in-differences, instrumental variables, and regression discontinuity—and five empirical examples: the effects of schooling, unions, immigration, military service, and class size. The chapter also covers data collection strategies, including secondary sources, primary data collection, and administrative data. It addresses measurement issues, such as measurement error models and the reliability of labor market data. The authors emphasize the importance of distinguishing between variables with causal effects, control variables, and outcome variables, and they discuss the challenges of generalizing findings from observational studies. The chapter highlights the growing use of quasi-experimental methods and the role of economic theory in causal modeling.