Building models with SAS Enterprise Miner, SAS Factory Miner, SAS Visual Data Mining and Machine Learning or just with programming

Using Tree Surrogate Imputation in SAS E-miner

Reply
New Contributor
Posts: 3

Using Tree Surrogate Imputation in SAS E-miner

Hello Everyone

 

I am using SAS e-miner 14.1 and I am trying to impute my missing values by using the "Tree Surrogate" option in the impute node of SAS e-miner but when I run the node the RESULTS TAB SHOWS THE  IMPUTED VALUE AS MISSING.

 

I have no problems when trying to impue it by Mean, Median, Mode etc, Are there any additional properties we need to set for Tree imputation?

 

Thanks.


Screen Shot 2017-01-06 at 11.41.32 PM.png
SAS Super FREQ
Posts: 272

Re: Using Tree Surrogate Imputation in SAS E-miner

I believe it's because there is not a single value that is used to impute in that case, rather it is based on the decision tree rules.  If you view the Score code in the Results of the Impute node, you should see how it is determining the imputation value.

Ask a Question
Discussion stats
  • 1 reply
  • 264 views
  • 0 likes
  • 2 in conversation