Hi,
I have a panel data, for which I try to use the adaptive LASSO model to identify the most important covariates. I am new in this area and appreciate your help. I run the following program (Instead of four covariates mentioned below, I have 45 independent variables).
proc glmselect data=infile;
model y=x1 x2 x3 x4/selection=LASSO(adaptive stop=none choose=bic);
run;
following is the LASSO selection summary in the results window. I wonder what the number effects column is in the following table. Is there any relation between this ranking and the importance of the variables? (I noticed that this ranking is not based on the size of the reduction in BIC)
The GLMSELECT Procedure | ||||
LASSO Selection Summary | ||||
Step | Effect | Effect | Number | BIC |
Entered | Removed | Effects In | ||
0 | Intercept | 1 | 474393.91 | |
1 | x3 | 2 | 474313.58 | |
2 | x1 | 3 | 474273.03 | |
3 | x2 | 4 | 473892.46* | |
Thanks.
I think should check the value of BIC-lag(BIC)
I think should check the value of BIC-lag(BIC)
Don't miss out on SAS Innovate - Register now for the FREE Livestream!
Can't make it to Vegas? No problem! Watch our general sessions LIVE or on-demand starting April 17th. Hear from SAS execs, best-selling author Adam Grant, Hot Ones host Sean Evans, top tech journalist Kara Swisher, AI expert Cassie Kozyrkov, and the mind-blowing dance crew iLuminate! Plus, get access to over 20 breakout sessions.
Use this tutorial as a handy guide to weigh the pros and cons of these commonly used machine learning algorithms.
Find more tutorials on the SAS Users YouTube channel.