Psychometrika

, Volume 55, Issue 3, pp 449–460 | Cite as

Easy bayes estimation for rasch-type models

  • Robert J. Jannarone
  • Kai F. Yu
  • James E. Laughlin
Article

Abstract

A Bayes estimation procedure is introduced that allows the nature and strength of prior beliefs to be easily specified and modal posterior estimates to be obtained as easily as maximum likelihood estimates. The procedure is based on constructing posterior distributions that are formally identical to likelihoods, but are based on sampled data as well as artificial data reflecting prior information. Improvements in performance of modal Bayes procedures relative to maximum likelihood estimation are illustrated for Rasch-type models. Improvements range from modest to dramatic, depending on the model and the number of items being considered.

Key words

Rasch model conjugate Bayes estimation artificial data augmentation conjunctive Markov models machine learning neural learning models 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Anderson, E. B. (1980).Discrete statistical models with social science applications. Amsterdam: North Holland.Google Scholar
  2. Bickel, P., & Doksum, K. (1977).Mathematical statistics: Basic ideas and selected topics. SAn Francisco: Holden-Day.Google Scholar
  3. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete datavia the EM algorithm.Nournal of the Royal Statistical Society, Series B,39, 1–38.Google Scholar
  4. Hambleton, R. K., & Swaminathan, H. (1984).Item response theory: Principles and applications. The Hague: Nihoff/Kluwer.Google Scholar
  5. Jannarone, R. J. (1987).Locally depdent models of reflecting learning abilities (Tech. Rep. #87-67). Columbia, SC: University of South Carolina, Center for Machine Intelligence.Google Scholar
  6. Jannarone, R. J., Yu, Kai, F., & Takefuji, Y. (1988). “Conjunctoids”: Probabilistic learning models for binary events.Neural Networks, 1, 355–337.Google Scholar
  7. Mislevy, R. J. (1986). Bayes modal estimation in item response models.Psychometrika, 51, 177–195.Google Scholar
  8. Novick, M. R., & Jackson, P. H. (1974).Statistical methods for educational and psychological research. New York: McGraw-Hill.Google Scholar
  9. Swaminathan, H., & Gifford, J. A. (1981, June).Bayesian estimation for the three-parameter logistic model. Paper presented at the annual Psychometric Society meetings, Chapel Hill, NC.Google Scholar
  10. Swaminathan, H., & Gifford, J. A. (1982). Bayesian estimation in the Rasch model.Journal of Educational Statistics, 7, 175–197.Google Scholar
  11. Swaminathan, H., & Gifford, J. A. (1985). Bayesian estimation for the one-parameter logistic model.Psychometrika, 47, 349–364.Google Scholar
  12. Tanner, M., & Wong, W. H. (1987). The calculation of posterior distributions by data augmentation.Journal of the American Stastistical Association, 82, 528–540.Google Scholar
  13. Tsutakawa, R. K., & Lin, H. Y. (1986). Bayesian estimation of item response curves.Psychometrika, 51, 251–267.Google Scholar
  14. Wright, B. (1986).Bayes' answer to perfection. Unpublished Manuscript. University of Chicago.Google Scholar

Copyright information

© The Psychometric Society 1990

Authors and Affiliations

  • Robert J. Jannarone
    • 1
  • Kai F. Yu
    • 1
  • James E. Laughlin
    • 1
  1. 1.Department of Electrical and Computer EngineeringUniversity of South CarolinaColumbia

Personalised recommendations