Prev: NEW: Power User's Guide to SAS Programming by Philip R Holland (published Dec2008)
Next: Lab Tables
From: Peter Flom on 15 Dec 2008 06:41
paul wilson <paulwilsn(a)YAHOO.COM> wrote
>I recently saw people use this code in their PROC LOGISTIC:
>
>ctable pprob=.4
>
>
>I tried including it in my syntax just to see what it does and if I really need it ,so the new code
>looks like this:
>
>proc logistic data = penalty
> outest=scoring_coeff;
> model death (event='1')=blackd whitvic serious/ rsq influence ctable pprob=.4
> clparm=both
> outroc=work._logroc;
> run;
>
<<<
>Apparently ctable produces some sort of classificiation table, but to me it looks pretty much the same to the dataset created by the "outroc" statement. I just wanted to consult the list this is the case before I get rid of it so I'd appreciate if
>someone could confirm.
>>>>

They do look like they produce the same output. I've been using CTABLE, but it looks like outroc will also be useful. One difference (which has good and bad points) is that CTABLE seems, at least by default, to print to the OUTPUT window, while OUTROC produces a data set.

I've actually mentioned CTABLE in a talk that I've given several times, and no one has mentioned OUTROC, so it doesn't seem to be well known.

<<<<
My second question is about "pprob". Just from playing around with different settings, it doesn't look like this code has any effects on the models coefficients, odds ratios etc. Is that true?

I'm assuming it is only used for classification of cases based on the p value cut off point assigned (i.e. pprob = .4 means that every case that crosses
..4 threshold is classified as "event = 1") and not for coefficient estimation. Can anyone clarify and explain?
>>>>>

I am not sure what is left to clarify or explain - that's exactly what ctable does. You set pprob to whatever list of values you like, and you get the sensitivity, specificity and so on for those levels of probability

Peter

Peter L. Flom, PhD
Statistical Consultant
www DOT peterflom DOT com
 | 
Pages: 1
Prev: NEW: Power User's Guide to SAS Programming by Philip R Holland (published Dec2008)
Next: Lab Tables