Hi, I'm trying to understand how EM calculates the no. of events vs non-events in each ranked demi-decile after adjusting for prior probabilities. In my original data, I have 1% events and 99% non-events. In my sample data for model development, I have 20% events and 80% non-events. I apply a random forest to my sample data. The model predicts that I have in my 1st bin (i.e. demi-decile with the highest scores), 343 true events and 23 true non-events. After applying the decision node to my model results, I now have in my 1st bin (i.e. the demi-decile with the highest ADJUSTED scores), 36 true events and 332 true non-events. How was this actually determined? I understand how the posterior probabilities are adjusted but I don't understand how the no. of true events and non-events are adjusted. Appreciate if someone can help to explain this.
... View more