https://communities.sas.com/t5/Statistical-Procedures/Predictive-Probabilities-cut-offs-for-binary-ourcome/m-p/427444#M22469 <P>IF you are using PROC LOGISTIC . Check options of MODEL.</P> <P>&nbsp;</P> <P>CTABLE Displays the classification table<BR />PPROB= Specifies probability cutpoints for classification</P> Sat, 13 Jan 2018 11:16:25 GMT Ksharp 2018-01-13T11:16:25Z https://communities.sas.com/t5/Statistical-Procedures/Predictive-Probabilities-cut-offs-for-binary-ourcome/m-p/427250#M22456 <P>Hi All</P><P>I have built a predictive model in sas EM for predicting "no shows". The probability of&nbsp; high majority of cases&nbsp; of no show are between 0.57 to 0.68. Based on our business decision we came up with cut offs of 0.57. But I am not convinced to do overbooking&nbsp; &nbsp;with cases who have just crossed the cut off line like 0.59.&nbsp;</P><P>Isnot&nbsp; these cases have only 9 % more likely to be no show compared to random 50 50 chance ( like flip of coin)?</P><P>&nbsp;</P><P>Please advise&nbsp;</P><P>Thank you so much</P><P>&nbsp;</P> Fri, 12 Jan 2018 16:26:54 GMT https://communities.sas.com/t5/Statistical-Procedures/Predictive-Probabilities-cut-offs-for-binary-ourcome/m-p/427250#M22456 chuie 2018-01-12T16:26:54Z https://communities.sas.com/t5/Statistical-Procedures/Predictive-Probabilities-cut-offs-for-binary-ourcome/m-p/427444#M22469 <P>IF you are using PROC LOGISTIC . Check options of MODEL.</P> <P>&nbsp;</P> <P>CTABLE Displays the classification table<BR />PPROB= Specifies probability cutpoints for classification</P> Sat, 13 Jan 2018 11:16:25 GMT https://communities.sas.com/t5/Statistical-Procedures/Predictive-Probabilities-cut-offs-for-binary-ourcome/m-p/427444#M22469 Ksharp 2018-01-13T11:16:25Z