ABSTRACT
This chapter introduces linear regression modeling for complex sample survey data, its similarities and how it differs (theoretically and procedurally) from standard ordinary least squares (OLS) regression analysis. It presents a brief history of important statistical developments in linear regression analysis of complex sample survey data. Kish and Frankel were two of the first to empirically study and discuss the impacts of complex sample designs on inferences related to regression coefficients. Regression analysis is a study of the relationships among variables: a dependent variable and one or more independent variables. There are four basic steps that analysts should follow when fitting regression models to complex sample survey data: specification, estimation, evaluation (diagnostics), and inference. These steps apply to all types of regression models and not just those discussed in this chapter for continuous response variables.
