topic how to calculate overall hit rate of logistic model? in Statistical Procedures https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101996#M5379 <HTML><HEAD></HEAD><BODY><P>I built one logistic model on my data (my dependent variable includes four nominal category data). I'm wondering if proc logistic provides one way to calculate overall hit rate?</P><P>Anyone has experience about this?</P><P></P><P>Any help will be appreciated...........Thanks</P></BODY></HTML> Sun, 08 Jul 2012 02:09:12 GMT MikeTurner 2012-07-08T02:09:12Z how to calculate overall hit rate of logistic model? https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101996#M5379 <HTML><HEAD></HEAD><BODY><P>I built one logistic model on my data (my dependent variable includes four nominal category data). I'm wondering if proc logistic provides one way to calculate overall hit rate?</P><P>Anyone has experience about this?</P><P></P><P>Any help will be appreciated...........Thanks</P></BODY></HTML> Sun, 08 Jul 2012 02:09:12 GMT https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101996#M5379 MikeTurner 2012-07-08T02:09:12Z Re: how to calculate overall hit rate of logistic model? https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101997#M5380 <HTML><HEAD></HEAD><BODY><P>Does this paper help? <A href="http://www2.sas.com/proceedings/sugi24/Stats/p261-24.pdf">http://<CITE>www2.sas.com/proceedings/sugi24/Stats/p261-24.pdf</CITE></A></P></BODY></HTML> Mon, 09 Jul 2012 20:35:48 GMT https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101997#M5380 ballardw 2012-07-09T20:35:48Z Re: how to calculate overall hit rate of logistic model? https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101998#M5381 <HTML><HEAD></HEAD><BODY><P>You have 4 levels of your dependent variable so you have a nominal logit model, is that what you were after?</P><P>For simple logistic regression with binary dependent variable then SAS would give you percent concordant/discordant which is what you're after I think.</P><P>You could output the predicted values and then calculate it manually:</P><P></P><P>output out =pred predprob=(individual);</P><P></P><P>I don't know anything about your data, but if its a classification problem then proc discrim may be what you're after. </P></BODY></HTML> Mon, 09 Jul 2012 21:10:38 GMT https://communities.sas.com/t5/Statistical-Procedures/how-to-calculate-overall-hit-rate-of-logistic-model/m-p/101998#M5381 Reeza 2012-07-09T21:10:38Z