BookmarkSubscribeRSS Feed
fallanir
Fluorite | Level 6

Hi all,

I am trying to build a Logistic Regression model using the typical Train-Validate-Test approach for effect selection. In the documentation, proc HpLogistic is supposed to have a Partition statement allowing you to separate your data into three sets, and you can then use Choose=Validate in the Selection statement to choose effects based on the validation error. However, in my version of SAS, I cannot implement the Partition statement--it isn't recognized at all.

I am using SAS 9.4, Enterprise Guide 7.1. It has HpLogistic, but without the Partition option.

Any help on why I cannot use this, and/or how to achieve the same result perhaps using a different SAS procedure, would be greatly appreciated.

6 REPLIES 6
Reeza
Super User
Do you get an error? If so post you log.

Also, what is your exact sas version, there are 3 9.4 releases to daye.
fallanir
Fluorite | Level 6

SAS doesn't recognize the command "Partition"--instead of turning blue, the text "Partition" remains red. If I try to run the code, I get the error: "Error 180-322: Statement is not valid or it is used out of proper order."

 

The version of SAS I am using is 9.4_M1.

 

Reeza
Super User

The editor doesn't always highlight correctly.

 

Post your code and log. If you made a mistake in your code that would also happen. 

We can't help with the information you've provided.

fallanir
Fluorite | Level 6

Alright, please find attached my SAS code and the corresponding log.

Thanks!

yairg
Calcite | Level 5

I got in similar situation is it been solved?

Reeza
Super User
Same answer as before, post your code and then we can see.

sas-innovate-2024.png

Available on demand!

Missed SAS Innovate Las Vegas? Watch all the action for free! View the keynotes, general sessions and 22 breakouts on demand.

 

Register now!

What is ANOVA?

ANOVA, or Analysis Of Variance, is used to compare the averages or means of two or more populations to better understand how they differ. Watch this tutorial for more.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 6 replies
  • 1977 views
  • 2 likes
  • 3 in conversation