>wold appreciate suggestions Frank Harrell: Regression Modeling Strategies. Springer. >I tried both methods Could you say what you did? Did you have a true model that the data were generated from, that the two methods were trying to find? >predictors significant at 95% level. I assume you mean 5%. Blaise F Egan ----Original message---- From : [log in to unmask] Date : 18/02/2015 - 19:04 (GMTST) To : [log in to unmask] Subject : multiple regression method sensitivity multiple regression method sensitivity Stepwise regression is generally not recommended for multiple regression. Best subset is generally recommended instead? [sorry reference not to hand, wold appreciate suggestions] So being an empiricist I tried both methods on 52 sets of data with 21 potential predictors. I was surprised by results. There was a BIG difference in which method was most sensitive in terms of identifying predictors significant at 95% level. Most sensitive method identified a mean of 6 predictors, min=3, max =10 Least sensitive method identified a mean of 4.25 predictors, min=2, max = 7 Care to guess which method was most sensitive and explain why? Professor Diana Kornbrot email: : [log in to unmask] web: http://dianakornbrot.wordpress.com/ http://go.herts.ac.uk/diana_kornbrot Work Department of Psychology School of Life and Medical Sciences University of Hertfordshire College Lane, Hatfield, Hertfordshire AL10 9AB, UK voice: +44 (0) 170 728 4626 Home 19 Elmhurst Avenue London N2 0LT, UK voice: +44 (0) 208 444 2081 mobile: +44 (0) 740 318 1612 You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank. You may leave the list at any time by sending the command SIGNOFF allstat to [log in to unmask], leaving the subject line blank.