1
$\begingroup$

thank you for taking time out to read this.

I have previously ran ROC curves to get the AUCs for single test variables but I do not know how to derive the AUC for combined variables (2 test variables instead of just 1). I read that I can use logistic regression to get the AUC but I have no clue on how to do it and how to interpret the output. The system I'm using is SPSS version 22.

Please help. Thank you

$\endgroup$
3
$\begingroup$

I was advised that I can run a binary logistic regression to get the probability and then run a ROC curve using the probability as the test variable.

The whole process goes like this,

1) Analyse 2) Regression 3) Binary logistic, put in the state variable as the dependent variable, subsequently enter the variables you wish to combine into the covariates, then click on "save" and check the box "probabilities". This process will compute a new variable in your SPSS database, termed "PRE_1". 4) Run the ROC curve using "PRE_1" as test variable. 5) Obtain the result.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.