BookmarkSubscribeRSS Feed
deleted_user
Not applicable
I am a new SAS user from Viet Nam, I try the logistic regression, I have built the model & I want to test the accuracy of this model by using other data set, but I don't how to do it.
2 REPLIES 2
datalligence
Fluorite | Level 6
I guess you are talking about classifying new observations. In proc logistic, use the outmodel option. This saves the fitted model information in a data set. For example,

proc logistic data=training_data outmodel=mylib.Fitted_Model;
....
....

Use the above data Fitted_Model to model your new dataset,

proc logistic noprint inmodel=mylib.Fitted_Model;
score data=New_Data out=Scored_Data;
....

Scored_Data will have the data and the predicted values.

Romakanta
deleted_user
Not applicable
You can use Lift charts.

Lift charts are visual aids for measuring model performance. They consist of a lift curve and a baseline. The greater the area between the lift curve and the baseline, the better the model.

----
Calculate the model score in the other data set. Sort it by score and make 10 deciles.. Find out the sum of response and make the lift chart..

Regards
Vinux aka Richie

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!

Multiple Linear Regression in SAS

Learn how to run multiple linear regression models with and without interactions, presented by SAS user Alex Chaplin.

Find more tutorials on the SAS Users YouTube channel.

Discussion stats
  • 2 replies
  • 901 views
  • 0 likes
  • 2 in conversation