This is a statistics-oriented course that focuses on various aspects of regression analysis (general and generalized linear models). Topics to be covered include, but are not limited to, simple correlation and regression, multiple regression (with and without interaction/moderation terms, with/without nonlinear terms, contrast variable coding for categorical predictors, nested model comparison for hierarchical regression, etc.), regression diagnostics (outlying and influential cases identification and assessment, collinearity evaluation, residual analysis, etc.), logistic regression (with a comparison of the logit model with other commonly used classification models like probit model, decision tree model, etc.), among other things. The course will familiarize students with cleaning data for regression analysis, building regression models, conducting statistical inference of regression models, selecting the optimal regression model(s) for the data in hand, and interpreting regression analysis results using the right language. Students will gain requisite foundation knowledge necessary to learn more complex statistical tests and procedures, and become more critical of statistical presentations in academic journals and the mass media. Students will also become proficient in using at least one major statistics computer program (SPSS, Minitab, SAS, Stata, or R).
Prerequisite(s):   EPE/EDP 558 or consent of instructor
Same as EPE 660
Syllabi (Requires Link Blue/MyUK credentials)
Fall 2019
  Section 201 - Joseph Waddington (Adobe Acrobat PDF)
Spring 2019
  Section 001 - Joseph Waddington (Adobe Acrobat PDF)
Fall 2018
  Section 201 - Xin Ma (Adobe Acrobat PDF)
Spring 2018
  Section 001 - Joseph Waddington (Adobe Acrobat PDF)
Fall 2017
  Section 001 - Joseph Waddington (Adobe Acrobat PDF)
Spring 2017
  Section 201 - Joseph Waddington (Adobe Acrobat PDF)
Fall 2016
  Section 001 - Joseph Waddington (Adobe Acrobat PDF)
Fall 2015
  Section 202 - Michael D. Toland (Adobe Acrobat PDF)
Return to Courses