Statistical Properties of K6-Reference-Cited by-同舟云学术

Statistical Properties of K6

Published:2024-01-16 Issue: Volume: Page:
ISSN:
Container-title:
language:
Short-container-title:

Author:

arvapally ruchitha¹,stern steven¹

Affiliation:

1. Stony Brook University

Abstract

Abstract We consider five different ways to estimate the effects of demographic and other variables on mental illness using data from the NSDUH. The first four methods use an aggregated K6 score, and the last uses the six individual K6 questions together. We identify many problems with using the K6 questions and their sum as a measure of mental illness. We think that the correlated ordered probit model are the best for fitting and understanding the data. But we also think that this method makes it clearer about the problems with K6 in general.

Publisher

Research Square Platform LLC

Reference76 articles.

1. Adjaye-Gbewonyo, D., Boersma, P.: Early Release of Selected Estimates Based on Data From the 2020 National Health Interview Survey. Division of Health Interview Statistics, National Center for Health Statistics (2021)

2. Qualitative Response Models: A Survey;Amemiya T;J. Econ. Lit.,1981

3. American Psychological Association: Medicaid and Psychology. (2011). https://www.apa.org/topics/managed-care-insurance/medicaid

4. Andrade, Laura, J., Caraveo-Anduaga, P., Berglund, R., Bijl, R., Kessler, O., Demler, E., Walters, C., Kýlýç, D., Offord, T., Üstün, Wittchen, H.-U.: Cross-National Comparisons of the Prevalences and Correlates of Mental Disorders. Bulletin of the World Health Organization. 78(4), 413–426 (2000)

5. Baldwin, M.: Explaining the Differences in Employment Outcomes Between Persons With and Without Mental Disorders. Unpublished manuscript (2005)