This course introduces the use of multiple linear regression and related techniques in the analysis of social data. The emphasis is applied, with a focus on the analysis of survey, administrative and other types of data most commonly used by social science researchers. Students will learn to use a major statistical package to analyze such social data. Special attention will be given to the specification of models including choice of control variables, the interpretation of results, handling missing data, and the challenges posed by reverse causality, omitted variable bias, endogeneity, and other issues that commonly arise in the analysis of social data. The course will briefly introduce elaborations of the linear regression model developed to address specific situations such as categorical dependent variables.