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

Exporting odds ratio in EM

Accepted Solution Solved
Reply
New Contributor
Posts: 4
Accepted Solution

Exporting odds ratio in EM

[ Edited ]

I just started working with an EM evalulation and have tried logistic regression models. I was able to find how to export the coefficient values, but am unable to figure out how to export the odds ratios into a csv/excel file. How can I accomplish this other than reading the text log output of the model?

 

Edit:

 

Trying to get a similar output as I can in Enterprise Guide

eg.jpg


Accepted Solutions
Solution
‎06-27-2016 06:08 PM
SAS Employee
Posts: 106

Re: Exporting odds ratio in EM

Hi.

 

Since you already have coefficients in a dataset, you can use the EXP() function in SAS  to  transform them to odds ratios, i.e., 

 

oddsratio=exp(coefficient);

 

Similar with the upper and lower confidence for the coefficients to compute the CI for the odds ratio.

 

Hope this helps. 

 

Ray

View solution in original post


All Replies
Solution
‎06-27-2016 06:08 PM
SAS Employee
Posts: 106

Re: Exporting odds ratio in EM

Hi.

 

Since you already have coefficients in a dataset, you can use the EXP() function in SAS  to  transform them to odds ratios, i.e., 

 

oddsratio=exp(coefficient);

 

Similar with the upper and lower confidence for the coefficients to compute the CI for the odds ratio.

 

Hope this helps. 

 

Ray

SAS Employee
Posts: 106

Re: Exporting odds ratio in EM

..or transform the coefficients in Excel, which appears to have an exp function: 

 

https://support.office.com/en-us/article/EXP-function-c578f034-2c45-4c37-bc8c-329660a63abe

 

 

 

New Contributor
Posts: 4

Re: Exporting odds ratio in EM

Thank you for your answer, and sorry for my delay!

SAS Employee
Posts: 106

Re: Exporting odds ratio in EM

Glad it helped.

 

Ray

☑ This topic is SOLVED.

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

Discussion stats
  • 4 replies
  • 398 views
  • 0 likes
  • 2 in conversation