Facilitated by Dr. Robert Kelchen
Most quantitative research studies employ a form of regression analysis to examine the relationship between some dependent, or outcome, variable and some independent, or predictor, variable(s). While this often seems straightforward at first, employing regression is sometimes complicated by the fact that datasets often contain dozens, or sometimes even hundreds, of variables. Answering research questions using regressions requires the researcher to consider the characteristics of the variables at hand (Are they string, binary, categorical, or continuous?) as well as how they may be related (Does theory posit a relationship? What are the conventions used in other studies of the topic?). This seminar addresses these issues, focusing on 1) identifying the type(s) of regression that are appropriate for a study 2) selecting the relevant dependent and independent variable(s) for a regression model, and 3) running a regression model in Stata.