09-23-2016 06:09 PM
I want to demonstrate that
a) LASSO regression is superior to stepwise selection for variable selection
b) LASSO regression is superior to linear regression for prediction
I would like to use PROC GLMSELECT in SAS 9.3 to illustrate this. Would anyone have a data set and some code to do so?
If you have just the data set but no code, that's fine - I would be glad to write it by myself.
If you have both the data and the code, that would be even better!
Thanks for your help.
09-23-2016 10:54 PM
Compare AIC BIC PRESS .... these model fit statistic with these two method. I don't understand your second question. LASSO is variable selection method ,not a regression method. There are some better method than LASSO , like Net-LASSO . Check the documentation .
09-28-2016 03:42 PM
Sorry - I could have phrased that second question better. Suppose I generate 2 different models:
a) one model is obtained from stepwise selection
b) one model is obtained from LASSO
I want to show that the predictive accuracy of Model B is higher than that of Model A.
As Wikipedia notes, LASSO enhances the predictive accuracy of a resulting statistical model.
Would you have an example data set that I can use to demonstrate this?
09-29-2016 04:31 AM
Yeah. LASSO would be better than STEPWISE . After using these two method with PROC GLMSELECT , Check the following fit statistics: AIC 2172.72685 AICC 2174.27787 SBC 1736.94624 ASE (Train) 24.18515 ASE (Validate) 25.74617 ASE (Test) 22.57297 I would expect LASSO has smaller value of these statistics than STEPWISE.
10-03-2016 11:07 AM
Could you please tell me where you got these statistics? Did you apply those methods to a data set? If so, could you please tell me where that data set comes from?
10-03-2016 10:36 PM