I am using the technical manual and am unsure if I am doing it correctly, or am even able to; Im trying to calculate a linear t-score for a scale not part of the test. The CRIN scale is on the MMPI-A-RF but not the MMPI-2-RF. I am doing a project that could really benefit from having the same linear t-scores for CRIN along with what I have in my dataset for the other validity scales. Please and thank you.
I'm not sure, but I think that if the scale does not "exist" on the adult form of the test, then there is no way to derive a standard score for it - other than simply using the norms from the adolescent version. If you do that, of course, you'll need to be explicit about the fact that you've done so & provide some sort of rationale for why it is appropriate and potentially important.
I stand prepared to be corrected by any of the real MMPI mavens out there! Speaking of which, you might want to contact one of them directly. Auke Tellegen, for example, had a lot to do with developing the restructured clinical scales. I think he is still somewhat active at the U. of Minnesota, and he is supposed to be a pretty approachable person.
T-scores are computed as follows:
Take the index (i.e., raw) score,
subtract from it the raw score mean,
multiply this difference by 10,
divide by the standard deviation,
and add 50.
[X - M] x 10
T = ----------------- + 50
S.D.
David - That is indeed how one calculates a standard T Score. But the problem here, I think, is that Jacob isn't looking to create his own norms (using his own sample as the basis for the T Scores). He's working with a standardized test that has well-established norms. But there don't seem to be any adult norms for the scale he's interested in.
I suppose he could just create T Scores based on his own sample - at least he would have an interval-type scale, and this would be okay for correlational purposes. But it would not be comparable to the other scale scores on the MMPI-2.
Dr's Joy and Nichols,
Thanks for your input I have to admit though, after posting the question I realized a mistake I had made; I was confusing linear T-scores with Uniform T-scores! I thought I needed to calculate Uniform T-scores, but those do not apply to validity scales. In my frazzled state I had posted this question, clearly showing my MMPI naivety, HA!
Anyhow, I spoke with my mentor about it, and it turns out I was calculating the T-score for CRIN correctly all along. The issue brought up by Stephen is important though. Since CRIN has no norms with adults, applying them in my project has to be cautious. So I spoke with a few MMPI experts about the best approach.
Thanks again, and I appreciate your comments,
Jacob
Linear vs. uniform T Scores - urgh. Formula for a headache! At least you don't need to compare with Base Rate Scores!
- Badges
- Science topic
- Similar topics
- Psychology
- Psychometrics