gabybarber Tracker
https://communities.sas.com/kntur85557/tracker
gabybarber TrackerFri, 11 Oct 2024 05:43:37 GMT2024-10-11T05:43:37ZRe: ROC Curve with Multiple Predictors
https://communities.sas.com/t5/SAS-Programming/ROC-Curve-with-Multiple-Predictors/m-p/715320#M220930
Thank you so much! It worked perfectly!<BR />Fri, 29 Jan 2021 15:28:13 GMThttps://communities.sas.com/t5/SAS-Programming/ROC-Curve-with-Multiple-Predictors/m-p/715320#M220930gabybarber2021-01-29T15:28:13ZROC Curve with Multiple Predictors
https://communities.sas.com/t5/SAS-Programming/ROC-Curve-with-Multiple-Predictors/m-p/714647#M220648
<P>I am trying to create an ROC curve using maternal race and smoking group as predictors with depression as the outcome. Below is the syntax, we have used to do this:</P><P> </P><DIV>ods graphics on;</DIV><DIV>PROC LOGISTIC DATA=d.pramsv1 plots=effect plots=ROC(id=sensit);</DIV><DIV>Class SMOKE2 MATRACE;</DIV><DIV>WHERE (ANSAMPLE=1);</DIV><DIV>MODEL PPDSTATUS(DESC) = SMOKE2 MATRACE;</DIV><DIV>roc 'Smoking with race' SMOKE2 MATRACE;</DIV><DIV>RUN;</DIV><DIV>ods graphics off;</DIV><DIV> </DIV><DIV>Our output for the ROC curve has several points labelled with their corresponding sensitivity (see below):</DIV><DIV><span class="lia-inline-image-display-wrapper lia-image-align-inline" image-alt="ROC w_ smoking and maternal race.png" style="width: 400px;"><img src="https://communities.sas.com/t5/image/serverpage/image-id/53979i589232282D010796/image-size/medium?v=v2&px=400" role="button" title="ROC w_ smoking and maternal race.png" alt="ROC w_ smoking and maternal race.png" /></span><P> Is there a way to determine which cutoffs for the variables correspond to each of these labelled sensitivities?</P><P> </P><P>Any help would be much appreciated! Thanks!</P></DIV>Wed, 27 Jan 2021 16:20:16 GMThttps://communities.sas.com/t5/SAS-Programming/ROC-Curve-with-Multiple-Predictors/m-p/714647#M220648gabybarber2021-01-27T16:20:16ZRe: Sensitivity and Specificity Output for an ROC Curve
https://communities.sas.com/t5/Statistical-Procedures/Sensitivity-and-Specificity-Output-for-an-ROC-Curve/m-p/712821#M34454
<P>One follow up question - I am trying to get the sensitivity and specificity for each of my exposure groups independent of the covariates I have included in the model. For example, my exposure variable is smoking (4 levels), and I have included the covariate sex in my model (2 levels). Right now, I get sensitivities and specificities for each combination of the smoking groups and sex (8 different sensitivities). I would just like to see sensitivity and specificity for each level of the exposure group (smoking), independent of sex. </P>Wed, 20 Jan 2021 18:30:32 GMThttps://communities.sas.com/t5/Statistical-Procedures/Sensitivity-and-Specificity-Output-for-an-ROC-Curve/m-p/712821#M34454gabybarber2021-01-20T18:30:32ZRe: Sensitivity and Specificity Output for an ROC Curve
https://communities.sas.com/t5/Statistical-Procedures/Sensitivity-and-Specificity-Output-for-an-ROC-Curve/m-p/712795#M34453
Thanks! That was exactly what I was looking for - to display the numerical<BR />values.<BR />Wed, 20 Jan 2021 17:19:13 GMThttps://communities.sas.com/t5/Statistical-Procedures/Sensitivity-and-Specificity-Output-for-an-ROC-Curve/m-p/712795#M34453gabybarber2021-01-20T17:19:13ZSensitivity and Specificity Output for an ROC Curve
https://communities.sas.com/t5/Statistical-Procedures/Sensitivity-and-Specificity-Output-for-an-ROC-Curve/m-p/712414#M34446
<P>I am using data from PRAMS (which uses a complex survey design) to create an ROC curve using predicted probabilities. How can I see the sensitivity and specificity for my various cutoffs, keeping in mind the complex sample?</P><P> </P><P>Thanks!</P>Tue, 19 Jan 2021 14:49:10 GMThttps://communities.sas.com/t5/Statistical-Procedures/Sensitivity-and-Specificity-Output-for-an-ROC-Curve/m-p/712414#M34446gabybarber2021-01-19T14:49:10ZRe: Creating an ROC Curve with Weighted Sample
https://communities.sas.com/t5/Statistical-Procedures/Creating-an-ROC-Curve-with-Weighted-Sample/m-p/710092#M34381
Thanks!<BR />Fri, 08 Jan 2021 00:22:00 GMThttps://communities.sas.com/t5/Statistical-Procedures/Creating-an-ROC-Curve-with-Weighted-Sample/m-p/710092#M34381gabybarber2021-01-08T00:22:00ZRe: Creating an ROC Curve with Weighted Sample
https://communities.sas.com/t5/Statistical-Procedures/Creating-an-ROC-Curve-with-Weighted-Sample/m-p/710057#M34379
My data (PRAMS data from the CDC) does have a complex sample design. Do you happen to know how to do an ROC curve with data that has a complex sample design?<BR /><BR />Thanks!<BR />Thu, 07 Jan 2021 21:28:00 GMThttps://communities.sas.com/t5/Statistical-Procedures/Creating-an-ROC-Curve-with-Weighted-Sample/m-p/710057#M34379gabybarber2021-01-07T21:28:00ZCreating an ROC Curve with Weighted Sample
https://communities.sas.com/t5/Statistical-Procedures/Creating-an-ROC-Curve-with-Weighted-Sample/m-p/710019#M34377
<P>I am trying to generate an ROC curve using the PROC LOGISTIC procedure (see example below that I am using as a guide):</P><P class="p1">descending data <SPAN class="s1">= pinedat </SPAN>plots<SPAN class="s1">=</SPAN>effect plots<SPAN class="s1">=</SPAN>ROC<SPAN class="s1">(</SPAN>id<SPAN class="s1">=prob); </SPAN></P><P class="p1">class <SPAN class="s1">alc /</SPAN>descending param <SPAN class="s1">= glm; </SPAN></P><P class="p1">model <SPAN class="s1">y = age alc ; </SPAN></P><P class="p1">roc <SPAN class="s2">'Age' </SPAN><SPAN class="s1">age; </SPAN></P><P class="p1">roc <SPAN class="s2">'Alcohol' </SPAN><SPAN class="s1">alc; </SPAN></P><P class="p1">roc <SPAN class="s2">'Age & Alcohol' </SPAN><SPAN class="s1">age alc ; </SPAN></P><P class="p1">roccontrast reference<SPAN class="s1">(</SPAN><SPAN class="s2">'Age & Alcohol'</SPAN><SPAN class="s1">) /</SPAN>estimate <SPAN class="s1">; </SPAN></P><P class="p1"> </P><P class="p1"><SPAN class="s1">However, my sample is weighted, and I'm not sure how to modify this to be used with PROC SURVEYLOGISTIC. Any help would be much appreciated. Thanks!</SPAN></P>Thu, 07 Jan 2021 19:51:53 GMThttps://communities.sas.com/t5/Statistical-Procedures/Creating-an-ROC-Curve-with-Weighted-Sample/m-p/710019#M34377gabybarber2021-01-07T19:51:53Z