Dear R helpers,
I'm trying to fit a model for prediction, but I have 18 variables to choose from. So, my question is what are the methods used for choosing the best and smallest subset out of those 18 to predict y ? I tried the common ways: std. and corr, multiple regression is hard because of all the possibile combinations I have to try, so any ideas?
Thank you,
Maha
_________________________________________________________________
_WL_Refresh_messenger_video_042008
[[alternative HTML version deleted]]