Models vs. Experts #6: Predicting Male Psychological Disturbance
MMPI in actuarial diagnosis of psychological disturbance among college males
- Cooke, J. K.
- Journal of Counseling Psychology, 14, 474-477
- A version of the paper can be found here.
- Want a summary of academic papers with alpha? Check out our free Academic Alpha Database!
An actuarial formula which reliably replicated 6 experienced clinicians’ ratings of the MMPI (Minnesota Multiphasic Personality Inventory) profiles of 200 college males was derived by linear regression techniques. The formula was able to duplicate the judges’ decisions more reliably (r = .91) than the judges were able to duplicate their own ratings at a later time (r = .83) or than they could agree among themselves (r = .80). The psychometric formula had the highest hit rate (85%) for the “nonpsychiatric” group, whereas the judges had the highest hit rate (74% and 84%, respectively) for the “campus psychiatric” and “hospital psychiatric” groups. Because the largest portion of a general college population is “nonpsychiatric,” this suggests that the psychometric formula had the highest hit rate for the overall male college population.
Estimate coefficient estimates from a multiple regression output relating MMPI scores to different psychiatric profiles as judged by experts (e.g., severe maladjustment–this person’s behavior should be so disturbed that hospitalization or serious difficulties with the environment seem imminent). The first finding is that the formulaic model does a great job replicating the results of the pooled ratings of the experts.
Note: Group 1 and Group 2 are 2 different samples of UNC undergrads that took MMPI tests in a psychology test. Nonpsychiatric are students who were not considering mental help; campus psychiatric sought mental help on campus; hospital psychiatric were students who had been hospitalized for mental issues.
This is where the study gets interesting. The author looks at how well the formula and the experts can replicate their original findings:
- Model replicated itself, obviously: 91% correlation with the experts’ assessment
- Individuals experts came to the same conclusion 83% of the time.
- Pooled expert opinion came to the same conclusion 80% of the time.
What the heck? Looking at the same data, experts come to much different conclusions?
Thoughts on the paper?
Note: This site provides NO information on our value investing ETFs or our momentum investing ETFs. Please refer to this site.
Join thousands of other readers and subscribe to our blog.
Please remember that past performance is not an indicator of future results. Please read our full disclosures. The views and opinions expressed herein are those of the author and do not necessarily reflect the views of Alpha Architect, its affiliates or its employees. This material has been provided to you solely for information and educational purposes and does not constitute an offer or solicitation of an offer or any advice or recommendation to purchase any securities or other financial instruments and may not be construed as such. The factual information set forth herein has been obtained or derived from sources believed by the author and Alpha Architect to be reliable but it is not necessarily all-inclusive and is not guaranteed as to its accuracy and is not to be regarded as a representation or warranty, express or implied, as to the information’s accuracy or completeness, nor should the attached information serve as the basis of any investment decision. No part of this material may be reproduced in any form, or referred to in any other publication, without express written permission from Alpha Architect.
Definitions of common statistics used in our analysis are available here (towards the bottom)