Hi all,   I want to minimize the euclidean distance between the point (0,1) and my ROC curve. I have trained my logistic model in the set train2007 and want to test the model on the set pred2008. I have tried this code:     proc logistic data=sasdata.train2007; model flag(event="1") = TL_TA EAT_TA / CTABLE outroc=troc; score data=sasdata.pred2008 out=valpred outroc=vroc; roc; roccontrast; run;     the thing is, CTABLE only gives me the misclassification for the train2007 dataset. I want to find the misclassification for the pred2008 dataset and find the optimal cut off point by minimizing the euclidean distance in that dataset. ... View more

Hi all,   i want to make a ROC curve for an hold out sample. The thing is, i made a logistic regression for some data i have from the year 2007 and I want to see how this model fits the data in the year 2008. I can't use this code:   proc logistic data = sasdata.Data2008; model flag(event='1')=TL_TA EAT_TA AGE /outroc=r; run;     because then my model and my ROC curve is based on a logistic regression on the 2008 dataset. I want to do a logistc regression on the 2007 set, and then use this fit to see how it fits the 2008 data set. So i tried this:       proc logistic data=sasdata.data2007; class AGE (ref='Ny') / param = ref; model flag(event="1") = TL_TA EAT_TA AGE / CTABLE outroc=troc; score data=sasdata.data2008 out=valpred outroc=vroc; roc; roccontrast; run;     This seems ok. I get a ROC curve both for the fit of 2007 and then a ROC curve for how the 2007 model fits on the 2008 model. The thing is, i want to find the optimale cutoff point in 2008, where the euclidean distance from 1.0 is minimized to the ROC curve, how can i do that? The ctable option gives me the predicted probabilities for the 2007 data set only.   I hope you can help. ... View more

Hello all,   I have a small problem with the look of my ROC curve. My dataset looks like this:   company                       total assets                 city                           flag   1                                      32432                       Boston                      0 2                                      32213                       New York                  1 3                                      12341                       Chicago                    0 4                                      32124                       Boston                      0 .                                       .                                 . .                                       .                                 . .                                       .                                 . 23626                              7563                         Chicago                    0     So, we have observations on 23626 companies, with financials (there are more then just total assets), city and a flag, which says 0 if the company is not bankrupt or 1 if the company is bankrupt. So, i'm fitting a logistic regression, like this:     proc logistic data=have plots(only)=(roc(id=obs) effect); class city (ref='chicago') / param = ref; model flag(event='1') = TA EAToTA city; run;   I get a curve like the one attached. Why does my curve look like that? I thought it should only be a line and not some sort of band? Does it have something to do with the number of observations which is 23626 ?     Furtheremore i would like to know how to get 3 curves in the same graph. As if i have 3 datasets, like the one above, and then two others with the same companies, just from a different year.   Thank you,   yocrashi   ... View more