topic low correlations between the dependent and independents in SAS Programming https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99166#M257979 <HTML><HEAD></HEAD><BODY><P><SPAN style="color: #008000; font-size: 12pt; font-family: Courier New;">&nbsp; </SPAN></P><P>I am using a logistic regression and my biggest problem is the very low correlations between the dependent and independents. The highest correlation with the dependent variable is a spend variable with a boxcox transformation and yield only a correlation of 0.2. </P><P>The results of my model are not very impressive and this, I beleive, it is related to the fact that all of the variables have a correlation lower or equal to 0.2 with the dependent, </P><P>the area under the curve is 0.684 and the classification table is below. on final note, I did try different transformations on all independents and interactions as well.</P><P>Did someone had a similar experience?</P></BODY></HTML> Fri, 05 Apr 2013 17:41:38 GMT sasuser1000 2013-04-05T17:41:38Z low correlations between the dependent and independents https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99166#M257979 <HTML><HEAD></HEAD><BODY><P><SPAN style="color: #008000; font-size: 12pt; font-family: Courier New;">&nbsp; </SPAN></P><P>I am using a logistic regression and my biggest problem is the very low correlations between the dependent and independents. The highest correlation with the dependent variable is a spend variable with a boxcox transformation and yield only a correlation of 0.2. </P><P>The results of my model are not very impressive and this, I beleive, it is related to the fact that all of the variables have a correlation lower or equal to 0.2 with the dependent, </P><P>the area under the curve is 0.684 and the classification table is below. on final note, I did try different transformations on all independents and interactions as well.</P><P>Did someone had a similar experience?</P></BODY></HTML> Fri, 05 Apr 2013 17:41:38 GMT https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99166#M257979 sasuser1000 2013-04-05T17:41:38Z Re: low correlations between the dependent and independents https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99167#M257980 <HTML><HEAD></HEAD><BODY><P>I can't recall if this ever happened to me, but low correlations usually mean poor model fit</P></BODY></HTML> Fri, 05 Apr 2013 19:16:23 GMT https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99167#M257980 PaigeMiller 2013-04-05T19:16:23Z Re: low correlations between the dependent and independents https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99168#M257981 <HTML><HEAD></HEAD><BODY><P>After my posting, I have added a new variable from the database to my list of predictors and the distribution was bimodal which led me to think that my sample is including two different kind of population, i have corrected this and correlations are now fine</P></BODY></HTML> Fri, 05 Apr 2013 19:25:39 GMT https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99168#M257981 sasuser1000 2013-04-05T19:25:39Z Re: low correlations between the dependent and independents https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99169#M257982 <HTML><HEAD></HEAD><BODY><P>This is a super good example of how important data visualization is to good analysis.</P><P></P><P>Steve Denham</P></BODY></HTML> Mon, 08 Apr 2013 17:03:38 GMT https://communities.sas.com/t5/SAS-Programming/low-correlations-between-the-dependent-and-independents/m-p/99169#M257982 SteveDenham 2013-04-08T17:03:38Z