Advertisement

Sozial- und Präventivmedizin

, Volume 46, Issue 6, pp 369–378 | Cite as

Evaluating composite health measures using Rasch modelling: An illustrative example

Original Articles

Summary

Objectives

The purpose of the present article is to elucidate the opportunities provided by Rasch modelling in epidemiology and public health research in order to evaluate composite measures of health.

Methods

The article gives a review of Rasch modelling in conjunction with illustrative examples based on adolescent survey data.

Results

The article demonstrates how the Rasch-model enables examinations of the way items work across different samples/subgroups, e.g., detection of possible differential item functioning.

Conclusions

It is concluded that Rasch modelling may serve as a useful tool in the evaluation and the development of composite health measures intended to be used in epidemiology and public health research.

Key-Words

Rasch models Health Measurement 

Zusammenfassung

Fragestellung

Zweck des vorliegenden Artikels ist es, die Möglichkeiten des Rasch-Modells in der epidemiologischen und Public-Health-Forschung zwecks Auswertung zusammengesetzter Gesundheitsmasse zu erläutern.

Methoden

Der Artikel bietet einen Überblick über das Rasch-Modell in Verbindung mit erläuternden Beispielen, die auf statistischen Daten von Erwachsenen basieren.

Resultate

Der Artikel zeigt, wie das Rasch-Modell die Möglichkeit bietet, die Wirkung einzelner Fragen bei verschiedenen Auswahl-bzw. Untergruppen zu überprüfen, d. h. die Aufdeckung unterschiedlicher Funktionen bei Fragen zu ermöglichen.

Schlussfolgerungen

Als Schlussfolgerung gilt, dass das Rasch-Modell als geeignetes Instrument bei der Auswertung und Entwicklung zusammengesetzter Gesundheitsmasse dienen kann, die in der epidemiologischen und Public-Health-Forschung verwendet werden sollen.

Résumé

Objectifs

L'objectif de cet article est d'éclairer les possibilités offertes par le modèle de Rasch en matière d'épidémiologie et de recherche en santé publique afin d'évaluer des mesures composites de santé.

Méthodes

L'article étudie le modèle de Rasch apartis de données provenant d'études avec les adolescents.

Résultats

Il montre comment le modéle de Rasch permet de comprendre la manière dont les différentes variables fonctionnet dans divers échantillons, c'est à dire de détecter le fonctionnement des écarts éventuels entre les differentes variables.

Conclusions

En conclusion, le modèle de Rasch peut constituer un outil très utile dans l'évaluation et le développement de mesures de santé composites utilisées en épidémiologie ainsi qu'en recherche dans le domaine de la santé publique.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Andrich D. An elaboration of Guttman scaling with Rasch models for measurement. In: Brandon-Tuma N, ed. Sociological methodology. San Fransisco: Jossey-Bass, 1985: 33–80.Google Scholar
  2. 2.
    Thurstone LL. Attitudes can be measured. Am J Sociol 1928;33: 529–54.CrossRefGoogle Scholar
  3. 3.
    Andrich D. A scientific revolution in social measurement. Paper presented at the first meeting of the American Educational Research Association's Special Interest Group on Rasch Measurement. New Orleans, April 1988.Google Scholar
  4. 4.
    Rasch G. Probabilistic models for some intelligence and attainment tests. (First published 1960 by the Danish Institute for Educational Research). Chicago: MESA Press, 1980.Google Scholar
  5. 5.
    Rasch G. An informal report on the present state of a theory of objectivity in comparisons. In: Van der Kamp LJT, Vlek CAJ, eds. Psychological measurement theory: proceedings of the NUFFIC international summer session in science at “Het Oude Hof”, The Hague, July 14–28, 1966. Leyden: University of Leyden, 1967: 1–19.Google Scholar
  6. 6.
    Duncan OD. Notes on social measurement historical and critical. New York: Russel Sage Foundation, 1984.Google Scholar
  7. 7.
    Andrich D, Sheridan B, Luo G. RUMM2010: a windows interactive program for analysising data with Rasch Unidimensional Models for Measurement. Pertn, RUMM Laboratory, 2000.Google Scholar
  8. 8.
    Andrich D. Rasch Models for measurement. Newbury Park Sage, 1988.Google Scholar
  9. 9.
    Andrich D, van Schoubroeck L. The General Health Questionnaire: a psychometric analysis using latent trait theory. Psychol Med 1989;19: 469–85.PubMedCrossRefGoogle Scholar
  10. 10.
    Andrich D. Distinctions between assumptions and requirements in measurement in the social sciences. In: Keats JA, Taft R, Health RA, Lovibond SH, eds. Methematical and theoretical systems. North Holland: Elsevier Science Publishers BV, 1989: 7–16.Google Scholar
  11. 11.
    Rasch G. On general laws and the meaning of measurement in psychology. Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability. Berkely: University of California Press, 1961: 321–33.Google Scholar
  12. 12.
    Wright BD, Mok M. Rasch models overview. J Appl Meas 2000;1: 83–106.PubMedGoogle Scholar
  13. 13.
    Ryan JP. Introduction to Latent Trait Analysis and Item Response Theory. In: Hathaway WE, ed. Testing in the schools: new directions for testing and measurement, 19. San Fransisco: Jossey-Bass, 1983: 49–65Google Scholar
  14. 14.
    Streiner DL, Norman GR. Health measurement scales: a practical guide to their development and use. Oxford: Oxford University Press, 1995.Google Scholar
  15. 15.
    Wright BD, Stone MH. Best test design. Chicago: Mesa Press, 1979.Google Scholar
  16. 16.
    Andersen EB. What Georg Rasch would have thought about this book. In: Fischer GH, Molenaar IW, eds. Rasch models Foundations, recent developments, and applications. New York: Springer, 1995: 383–90.Google Scholar
  17. 17.
    Glas CAW, Verhelst ND. Testing the Rasch model. In: Fischer GH, Molenaar IW, eds. Rasch models Foundations, recent developments, and applications. New York: Springer, 1995: 69–95.Google Scholar
  18. 18.
    Van den Wollenberg AL. Testing a latent trait model. In: Langeheine R, Rost J, eds. Latent trait and latent class models. New York: Plenum Press, 1988: 31–50.Google Scholar
  19. 19.
    Hattie J. Methodology review: assessing unidimensionality of tests and items. Appl Psychol Meas 1985;9: 139–64.Google Scholar
  20. 20.
    Andersen EB. Sufficient statistics and latent trait models. Psychometrika 1977;42: 69–81.CrossRefGoogle Scholar
  21. 21.
    Andrich D. A rating formulation for ordered response categories. Psychometrika 1978;43: 561–73.CrossRefGoogle Scholar
  22. 22.
    andrich D. A model for contingency tables having an ordered response classification. Biometrics 1979;35: 403–15.CrossRefGoogle Scholar
  23. 23.
    Masters GN. A Rasch model for partial credit scoring. Psychometrika 1982;47: 149–74.CrossRefGoogle Scholar
  24. 24.
    Glas CAW, Verhelst ND. Tests of fit for polytomous Rasch models. In: Fischer GH, Molenaar IW, eds. Rasch models Foundations, recent developments, and applications. New York: Springer, 1995: 325–52.Google Scholar
  25. 25.
    Andrich D, de Jong JHAL, Sheridan BE. Diagnostic opportunities with the Rasch Model for ordered response categories. In: Rost J, Langeheine R, eds. Applications of latent trait and latent class models in the social sciences. Münster: Waxmann, 1997: 59–70.Google Scholar
  26. 26.
    Andrich D. A general form of Rasch's extended logistic model for partial credit scoring. Appl Meas Educ 1988:1: 363–78.CrossRefGoogle Scholar
  27. 27.
    Andrich D. Measurement criteria for choosing among models with graded responses. In: von Eye A, Clogg CC, eds. Categorical variables in developmental research. Methods of analysis. San Diego: Academic Press, 1996: 3–35.Google Scholar
  28. 28.
    Masters GN Item discrimination: when more is worse. J Educ Meas 1988:25: 15–29.CrossRefGoogle Scholar
  29. 29.
    Glass GV, Stanley JC. Statistical methods in education and psychology. New Jersey: Prentice-Hall, 1970.Google Scholar
  30. 30.
    Andrich D, Hagquist C. Taking account of differential item functioning through principles of equating. Perth: Social Measurement Laboratory, Murdoch University, 2001. (Research report; no 12, April 2001)Google Scholar
  31. 31.
    Heinen T. Latent class and discrete latent trait models: similarities and differences. Thousand Oaks: Sage, 1996.Google Scholar
  32. 32.
    Molenaar IW. Some background for item response theory and the Rasch model. In: Fischer GH, Molenaar IW, eds. Rasch models Foundations, recent developments, and applications. New York: Springer, 1995: 3–14.Google Scholar
  33. 33.
    Likert R. A technique for the measurement of attitudes. Arch Psychol (New York) 1932.Google Scholar
  34. 34.
    Duncan OD, Stenbeck M. Are Likert scales unidimensional? Soc Sci Res 1987:16: 245–59.CrossRefGoogle Scholar

Copyright information

© Birkhäuser Verlag 2001

Authors and Affiliations

  1. 1.Karlstad UniversityKarlstad

Personalised recommendations