, Volume 61, Issue 2, pp 313–330 | Cite as

Statistical inference based on latent ability estimates

  • Herbert Hoijtink
  • Anne Boomsma


The quality of approximations to first and second order moments (e.g., statistics like means, variances, regression coefficients) based on latent ability estimates is being discussed. The ability estimates are obtained using either the Rasch, or the two-parameter logistic model. Straightforward use of such statistics to make inferences with respect to true latent ability is not recommended, unless we account for the fact that the basic quantities are estimates. In this paper true score theory is used to account for the latter; the counterpart of observed/true score being estimated/true latent ability. It is shown that statistics based on the true score theory are virtually unbiased if the number of items presented to each examinee is larger than fifteen. Three types of estimators are compared: maximum likelihood, weighted maximum likelihood, and Bayes modal. Furthermore, the (dis)advantages of the true score method and direct modeling of latent ability is discussed.

Key words

item response theory true score theory latent ability estimates maximum likelihood weighted maximum likelihood Bayes modal latent regression 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Andersen, E. B. (1980). Comparing latent distributions.Psychometrika, 45, 121–134.Google Scholar
  2. Chang, H. H., & Stout, W. (1993). The asymptotic posterior normality of the latent trait in an IRT model.Psychometrika, 58, 37–52.Google Scholar
  3. Hacquebord, H. I. (1989).Tekstbegrip van Turkse en Nederlandse leerlingen in het voortgezet onderwijs [Text comprehension of Turkish and Dutch high school students]. Unpublished doctoral dissertation, University of Groningen.Google Scholar
  4. Hambleton, R. K., & Swaminathan, H. (1985).Item response theory. Boston: Kluwer-Nijhoff.Google Scholar
  5. Hoijtink, H., & Boomsma, A. (1991).Statistical inference with latent ability estimates (Heymans Bulletin, HB-91-1045-EX). Groningen: Rijksuniversiteit, Vakgroep Statistiek en Meettheorie.Google Scholar
  6. Lehmann, E. L. (1983).Theory of point estimation. New York: Wiley.Google Scholar
  7. Lord, F. M. (1983). Unbiased estimators of ability parameters, of their variance, and of their parallel-forms reliability.Psychometrika, 48, 233–245.Google Scholar
  8. Mislevy, R. J. (1991). Randomization based inferences about latent variables from complex samples.Psychometrika, 56, 177–196.Google Scholar
  9. Tatsuoka, M. M. (1988).Multivariate analysis. New York: MacMillan.Google Scholar
  10. Verhelst, N. D., & Eggen, T. J. H. M. (1989).Psychometrische en statistische aspecten van peilingsonderzoek (PPON-rapport nr. 4) [Psychometric and statistical aspects of survey research (PPON Report Nr. 4)]. Arnhem: CITO.Google Scholar
  11. Warm, T. A. (1989). Weighted likelihood estimation of ability in item response models.Psychometrika, 54, 427–450.Google Scholar
  12. Zwinderman, A. H. (1991). A generalized Rasch model for manifest predictors.Psychometrika, 56, 589–600.Google Scholar

Copyright information

© The Psychometric Society 1996

Authors and Affiliations

  1. 1.Department of Statistics and Measurement TheoryUniversity of GroningenGroningenThe Netherlands

Personalised recommendations