In this StatsClinic session, Dr. Ebuwa Igho-Osagie continues linear regression by unpacking R-squared and adjusted R-squared and what they really tell us about model fit. The class covers multiple linear regression, indicator variables, interaction terms, and how to interpret omnibus F-tests. Learners are guided through regression diagnostics, including residual plots, normality, heteroscedasticity, leverage, and influential observations. The session also introduces non-linear modeling using quadratic and cubic terms and explains when added complexity is justified. Finally, participants learn how to choose parsimonious models using likelihood ratio tests and AIC.
