BookmarkSubscribeRSS Feed
KenZ
Calcite | Level 5

I am using SAS EM for a logistic regression prediction. I found that sometimes I ran the nodes under the same conditions, but the result can be different (selection of variables ....).

I used stepwise iteration in the logistic regression, and imputed and transformed variables before running the regression node.

Your suggestion will be appreciated!

3 REPLIES 3
JasonXin
SAS Employee

Could you indicate EM version, OS (Windows....), and possibly share the xml diagram file? Jason Xin

Saszealot
Calcite | Level 5

I had similar experience but with SEM 6.1 and 7.1. They generate different outputs.

Sam_zirak
Fluorite | Level 6

If you have partitioned your dataset, you might get different results anytime you run your nodes if the "Rerun" feature on your "Input data" node has been set to "Yes". The reason is that  the partition node splits your dataset into "Training" and "Validation" randomly which could end up in getting slightly different results.

 

Sam

sas-innovate-2024.png

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.

 

Register now!

How to choose a machine learning algorithm

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.

Discussion stats
  • 3 replies
  • 1024 views
  • 1 like
  • 4 in conversation