Regression Analysis I: Introduction

Instructor(s):

Participants in this workshop should have mastered at least one semester of basic introductory statistics, including levels of measurement, descriptive statistics, sampling distributions, statistical inference, and hypothesis testing. The workshop introduces bivariate (one independent variable) and multivariate (multiple independent variables) linear regression models using elementary algebra, data visualizations, and applied examples from a range of social science literatures. Topics will include the development of the regression model, analysis of variance, parameter estimation, hypothesis testing, interpretation of estimates, model fit, non-linear and interaction terms, model predictions, an overview of some model diagnostics, and the practical implications of violating regression assumptions in a range of typical applications. The level of the course will be approximately that of Lewis-Beck's 'Applied Regression' (Sage) or Berry and Sanders’s 'Multiple Regression in Practice' (Sage) and with references to some topics covered in Fox’s 'Regression Diagnostics' (Sage).

Software: Lecture materials will include instructions and examples using SPSS and Stata, and support will be available for students who are already familiar with basic data analysis functions in R.

Fees: Consult the fee structure.

Tags: regression, least squares, bivariate regression, ANOVA, R-square, linear models, dummy variables, scalar regression, heteroscedasticity, Specification error, OLS, analysis of residuals

Course Sections