STAT 425 Week 09 - Analysis of Covariance (Ancova)

Analysis of covariance (Ancova) models include both numerical and categorical predictor variables. We discuss building and interpreting Ancova models, emphasizing the role of sequential F tests for model comparison. In order to include categorical variables in the multiple linear regression model we encode them, e.g., as 0/1 variables.  In R, categorical variables are referred to as 'factor' variables, and we can either encode the factor variables directly, or let the lm function do the encoding automatically if we supply category labels in the data frame.