Programming the statistical procedures from SAS

Regression Analysis

Accepted Solution Solved
Reply
Contributor
Posts: 65
Accepted Solution

Regression Analysis

Hello

 

In logistic regression as we split data into Training and Validation Samples.

 

Can we do the same in Linear regression?. If not please let me know why?.

 

Kafeel


Accepted Solutions
Solution
‎06-10-2016 06:52 PM
Grand Advisor
Posts: 9,444

Re: Regression Analysis

Yes. You could. But I would not recommend .

PROC REG is for predicted model ( interpolated data) , not for forecasted model (Extrapolated data) -- which is well-knowed  as Time Series Analysis .

 

If you use PROC REG for Extrapolated data, the model error would be very large, and model would not be trusted .

View solution in original post


All Replies
Grand Advisor
Posts: 16,842

Re: Regression Analysis

Yes, you can and should split your data for linear regression. 

This methodology is consistent across various statistical procedures not just

logistic regression. 

 

I'm not aware of an automatic method to factor in the diff datasets but I'd review the documentation. 

Solution
‎06-10-2016 06:52 PM
Grand Advisor
Posts: 9,444

Re: Regression Analysis

Yes. You could. But I would not recommend .

PROC REG is for predicted model ( interpolated data) , not for forecasted model (Extrapolated data) -- which is well-knowed  as Time Series Analysis .

 

If you use PROC REG for Extrapolated data, the model error would be very large, and model would not be trusted .

☑ This topic is SOLVED.

Need further help from the community? Please ask a new question.

Discussion stats
  • 2 replies
  • 159 views
  • 2 likes
  • 3 in conversation