The use of PEVENT= in Proc Logistic

[PaigeMiller]

---

@Lobbie wrote:

The only explanation I can think of i.e. as to why I do not need to specify PEVENT option contrary to the recommendation in the documentation is because I fitted the model using Weight statement.  All parameters are adjusted accordingly and are used to compute the CTABLE and P_1 probabilities in the scored dataset.  This is also the reason why I do not need to specify PRIOREVENT= in the score statement when scoring.

---

Hello again @Lobbie @StatDave @Ksharp 

The WEIGHT statement is not used for oversampling and correction of oversampling, is it? Or is that a use for the WEIGHT statement that I am not aware of?

I have always thought of the WEIGHT statement as it exists in every other PROC, if the weight variable equals 2, then this data point impacts the regression the same as if the data set had this data point twice with WEIGHT of 1.

[StatDave]

Yes, appropriate weighting based on the sampling is one way to adjust for oversampling as described in this note. Of course, the WEIGHT statement can also be used as in other procedures to apply differential weighting of the observations. 

[Lobbie]

This definitely cleared the confusion I had in regards to the use of PEVENT. 

 @StatDave .@PaigeMiller and @Ksharp , thank you for taking the time to answer this and the discussions.  much appreciated.