topic Re: Effects Plot and Coefficient Question in SAS Data Science https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174693#M2030 <HTML><HEAD></HEAD><BODY><P>Hi I have a quick answer for you.&nbsp; If you look at the legend below the chart, red is positive and blue is negative.&nbsp; That matches your Parameter Estimates.</P><P></P><P>Thanks,</P><P>Jonathan</P></BODY></HTML> Fri, 14 Feb 2014 14:39:53 GMT jwexler 2014-02-14T14:39:53Z Effects Plot and Coefficient Question https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174692#M2029 <HTML><HEAD></HEAD><BODY><P>Hi All,</P><P></P><P>I am running logistic regression model using variable selection, variable transform with maximum normal and then again variables transform with optimal binning. </P><P></P><P>I am getting quite good roc index and miss-classification rate.</P><P>In the effects plot I have many variables in blue (i guess that means positive effect) and one variable with red column (negative effect).</P><P>but in the Analysis of Maximum Likelihood Estimates many variables are negative and only one is positive i.e. exactly the opposite of the effect plot.</P><P></P><P>How to explain this? </P><P></P><P>Thank you!</P><P></P><P></P><P></P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Analysis of Maximum Likelihood Estimates</P><P></P><P>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Standard&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Wald</P><P>Parameter&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; DF&nbsp;&nbsp;&nbsp; Estimate&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Error&nbsp;&nbsp;&nbsp; Chi-Square&nbsp;&nbsp;&nbsp; Pr &gt; ChiSq&nbsp;&nbsp;&nbsp; Exp(Est)</P><P></P><P>OPT_Age&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-34.5&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -1.1347&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3570&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 10.10&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.0015&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.322</P><P>OPT_BMI&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-28.540152&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -0.9561&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3507&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 7.43&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.0064&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.384</P><P>OPT_FG&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-99.5, MISSING&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -0.3387&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3248&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1.09&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.2971&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.713</P><P>OPT_HDL&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-45.4&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.9830&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3946&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 6.21&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.0127&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 2.672</P><P>OPT_LDL&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-114.3, MISSING&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -0.5588&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.4448&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1.58&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.2091&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.572</P><P>OPT_Ratio_New 01:low-0.6322109, MISSING&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -0.7628&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3756&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 4.12&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.0423&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.466</P><P>OPT_TC&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-201.25, MISSING&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -0.1096&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.5006&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.05&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.8267&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.896</P><P>OPT_Tryg&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 01:low-190.2, MISSING&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 1&nbsp;&nbsp;&nbsp;&nbsp; -0.1636&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.3848&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.18&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.6706&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; 0.849</P></BODY></HTML> Fri, 14 Feb 2014 13:23:42 GMT https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174692#M2029 stataddict 2014-02-14T13:23:42Z Re: Effects Plot and Coefficient Question https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174693#M2030 <HTML><HEAD></HEAD><BODY><P>Hi I have a quick answer for you.&nbsp; If you look at the legend below the chart, red is positive and blue is negative.&nbsp; That matches your Parameter Estimates.</P><P></P><P>Thanks,</P><P>Jonathan</P></BODY></HTML> Fri, 14 Feb 2014 14:39:53 GMT https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174693#M2030 jwexler 2014-02-14T14:39:53Z Re: Effects Plot and Coefficient Question https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174694#M2031 <HTML><HEAD></HEAD><BODY><P>Thank you Jonathan!</P><P></P><P>So, the moral is: always look to the legend <span class="lia-unicode-emoji" title=":slightly_smiling_face:">🙂</span></P><P></P><P>regards,</P><P>Gio</P></BODY></HTML> Fri, 14 Feb 2014 15:11:27 GMT https://communities.sas.com/t5/SAS-Data-Science/Effects-Plot-and-Coefficient-Question/m-p/174694#M2031 stataddict 2014-02-14T15:11:27Z