We introduce a fast stepwise regression method, called the orthogonal greedy algorithm (OGA), that selects input variables to enter a p-dimensional linear regression model (with p ≫ n, the sample size ...

This note discusses a problem that might occur when forward stepwise regression is used for variable selection and among the candidate variables is a categorical variable with more than two categories ...

We describe how to conduct a regression analysis for competing risks data. The use of an add-on package for the R statistical software is described, which allows for the estimation of the ...

10.3.1 Scatterplot matrix Recall that we use SAS’s scatterplot matrix feature to quickly scan for pairs of explanatory variables that might be colinear. To do this in R we must first make sure we ...