Cross-validation is a resampling technique that can be used to evaluate the performance of predictive models. It is a general-purpose technique that can be used in many types of models including linear and generalized linear models, classification and regression trees, and other machine learning models as well as selecting model tuning parameters.
In this workshop, we discuss standard measures of model fit, validation set methods, leave-one-out cross-validation, K-fold cross-validation, and repeated K-fold cross-validation. Participants will learn how to choose an appropriate measure of fit and select a validation method for their own data. Familiarity with linear regression will be assumed. Methods will be demonstrated using examples in R, although no familiarity with R is required and the methods discussed can be implemented in other statistical software packages.