Hello I have a dataset with 151 dependent variables and estimated in 6 different conditions, and each condition is repeated 3 times. It si proteomic and therefore expensive, so few repetitions. I want to conduct a stepwise discriminant analysis to identify the variables that really matter. To do so, I will use greedy.wilks. and stepclass. However, I need to remove colinear variables to run these functions. Can anyone tell me how to identify the colinear variables to then remove them? Thank you in advance julien. -- View this message in context: http://r.789695.n4.nabble.com/remove-colinear-variables-tp4664077.html Sent from the R help mailing list archive at Nabble.com.