BookmarkSubscribeRSS Feed
TonyF
Calcite | Level 5

I tried to do a Regression Analysis (with backward elimination) for my data set  and it worked fine. However, when I tried to use Data Partition  to split the data into Training (60%) and Validation (40%), it comes with the error

The computed Average Squared Error for Ln_NW is 6.699147E-24.

    This indicates a possible target duplication issue.

    Please review the list of inputs used in the model."

1 REPLY 1
WendyCzika
SAS Employee

Hi Tony,

This message indicates that since the model is predicting almost perfectly (near-0 ASE), that there is likely an input variable that has identical or almost identical values as the target variable.  However, it is very strange that you didn't get that message when running with the un-partitioned data.  In the Results from the un-partitioned Regression, are you seeing a very small ASE?

Thanks,

Wendy

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!

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
  • 1 reply
  • 1901 views
  • 0 likes
  • 2 in conversation