topic Re: Adjusting Predicted probabilities in SAS Base in SAS Data Science

Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 13:21:27 GMT

Hi all,

I have the following situation, I have created a training and validation sample in which both the analogy of events/nonevents is the same thus 50-50.

I have fitted the training sample and tested my model on the validation sample (using proc logistic) with good results and i want to score now the initial population as a final test from which i made the two samples.

The initial population consists of 80% nonevents (0) and 20% events (1), if am not mistaken this means that i will have to adjust my predicted probabilities on the population to the true event rate since my model was build on a 50-50 analogy is that correct?

How could i do that in SAS Base? I mean which output from the logistic regression must I investigate and apply this alteration? Any ideas? If i could know how the predicted probability in the first case is calculated maybe i could adjust within that calculation.

Thank you in advance

Re: Adjusting Predicted probabilities in SAS Base

stat_sas — Tue, 06 May 2014 13:43:22 GMT

I think you oversampled the population to make event/non-event in 50-50 proportions in your training/validation samples. Check offset option in logistic regression to adjust predicted probabilities.

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 13:59:02 GMT

Exactly that's what I did, would you happen to have any example on the offset option syntax wise so i could understand it better?

Thanks

Re: Adjusting Predicted probabilities in SAS Base

stat_sas — Tue, 06 May 2014 14:08:51 GMT

See below

22601 - How do I adjust for oversampling the event level in a binary logistic model?

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 14:39:34 GMT

Thnx

Re: Adjusting Predicted probabilities in SAS Base

M_Maldonado — Tue, 06 May 2014 15:10:08 GMT

Thanks @stat@sas !
An awesome read... I stopped doing what I was doing just to read this even if I don't use base SAS (I use EM). Still, very nice article... Thanks!

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 15:33:13 GMT

One more question though, by using either prior or offset will i be adjusting the probabilities in the population data that i want to score or the already predicted probabilities in the training and validation set?

Re: Adjusting Predicted probabilities in SAS Base

stat_sas — Tue, 06 May 2014 16:40:38 GMT

Offset just aligns intercept it does not effect beta coefficients. Use offset in proc logistic using your training data set and get the parameter estimates. Score validation dataset using estimates obtained through training dataset. If you see results are almost similar then you can use this model for population dataset as well.

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 16:46:50 GMT

Ok , I was just under the impression that since the intercept gets "inflated" that would mean that the predicted probabilities would get inflated too ,thus they would need adjustment too, am I wrong?

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 16:49:29 GMT

Aha ok i misread since i am adjusting intercept I am good to go, so for scoring the validation which is also of a 50-50 analogy i dont need to adjust, that would be only for the population scoring where the true rates of events and non events is depicted

Re: Adjusting Predicted probabilities in SAS Base

stat_sas — Tue, 06 May 2014 16:54:55 GMT

That is correct. If the objective is to see significance of predictors only then you don't need to use offset.

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Tue, 06 May 2014 19:21:56 GMT

Thank you for your clarifications

Re: Adjusting Predicted probabilities in SAS Base

chemicalab — Wed, 07 May 2014 07:35:15 GMT

I have tried the following :

proc freq data=OUTPUT.POPULATION (THE SET WITH 95% nonevents and 5% events) noprint;

table TARGET / out=priors(drop=percent rename=(count=_prior_));

run;

and i try to score it with the parameters based on the training set:

PROC LOGISTIC INMODEL=MODELPARAMETERSTRAINING (the 50-50 sample) ;

SCORE DATA=OUTPUT.POPULATION PRIOR=PRIORS

OUTROC=ROC

OUT=SCORESPOP PREDICTED=ESTPROB

;

RUN;

Would that be the correct syntax? I am wondering cause when i compare the estimated probabilities of scoring with or without the priors i see a huge difference in p_1