topic Re: Additional R-Square for each logistic regression variable in SAS Programming https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187275#M303994 <HTML><HEAD></HEAD><BODY><P>Thank you Steve!</P><P></P><P>I went through the article and found it really interesting. </P><P>So, you suggest to go one by one with the independent variables, and calculate for each of them R^2. </P><P>Otherwise, I will get model R^2, not the R^2 for each independent variable....</P></BODY></HTML> Thu, 27 Feb 2014 11:37:50 GMT stataddict 2014-02-27T11:37:50Z Additional R-Square for each logistic regression variable https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187273#M303992 <HTML><HEAD></HEAD><BODY><P>Hi All,</P><P></P><P>I am trying to calculate additional R-Square for each regression variable, like in medical journals (cf. attached file).</P><P>Overall R-square is easy to locate, but how to calculate additional R-square for each variable?</P><P></P><P>Thank you!</P><BR /><IMG src="https://communities.sas.com/t5/image/serverpage/image-id/11294i29FB91C46D8F65F8/image-size/large?v=1.0&amp;px=600" border="0" alt="Additional R-Square.jpg" title="Additional R-Square.jpg" /></BODY></HTML> Wed, 26 Feb 2014 10:39:44 GMT https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187273#M303992 stataddict 2014-02-26T10:39:44Z Re: Additional R-Square for each logistic regression variable https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187274#M303993 <HTML><HEAD></HEAD><BODY><P>I am going to refer you to Paul Allison's webpage on R-square in logistic models (<A href="http://www.statisticalhorizons.com/r2logistic">http://www.statisticalhorizons.com/r2logistic</A>).&nbsp; I believe you could calculate an additional Rsquare using Tjur's method (see webpage) by fitting with and without each independent variable.&nbsp; It should be pretty easy to loop through all combinations to get what you are looking for.</P><P></P><P>Steve Denham</P></BODY></HTML> Wed, 26 Feb 2014 18:42:37 GMT https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187274#M303993 SteveDenham 2014-02-26T18:42:37Z Re: Additional R-Square for each logistic regression variable https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187275#M303994 <HTML><HEAD></HEAD><BODY><P>Thank you Steve!</P><P></P><P>I went through the article and found it really interesting. </P><P>So, you suggest to go one by one with the independent variables, and calculate for each of them R^2. </P><P>Otherwise, I will get model R^2, not the R^2 for each independent variable....</P></BODY></HTML> Thu, 27 Feb 2014 11:37:50 GMT https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187275#M303994 stataddict 2014-02-27T11:37:50Z Re: Additional R-Square for each logistic regression variable https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187276#M303995 <HTML><HEAD></HEAD><BODY><P>Not quite.&nbsp; What I think you want is to calculate the values for the full model first.&nbsp; Then calculate the values for the models, deleting each independent variable in turn.&nbsp; The difference between the full model value and the reduced models' values would give the "additional Rsquare" for each independent variable.&nbsp; So, you fit one model with N independent variables, and N models with N-1 independent variables, calculate the positive minus negative proportions for each, and then calculate the change in that value dependent on the independent variable in question.&nbsp; That may be exactly what you were saying and I apologize if I misinterpreted it.</P><P></P><P>Steve Denham</P></BODY></HTML> Thu, 27 Feb 2014 11:59:53 GMT https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187276#M303995 SteveDenham 2014-02-27T11:59:53Z Re: Additional R-Square for each logistic regression variable https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187277#M303996 <HTML><HEAD></HEAD><BODY><P>Somehow I deleted the posts <img id="smileysad" class="emoticon emoticon-smileysad" src="https://communities.sas.com/i/smilies/16x16_smiley-sad.png" alt="Smiley Sad" title="Smiley Sad" /> How to restore them???</P></BODY></HTML> Fri, 28 Feb 2014 09:33:08 GMT https://communities.sas.com/t5/SAS-Programming/Additional-R-Square-for-each-logistic-regression-variable/m-p/187277#M303996 stataddict 2014-02-28T09:33:08Z