The Annals of Statistics

Posterior convergence given the mean

B. Clarke and J. K. Ghosh

Full-text: Open access


For various applications one wants to know the asymptotic behavior of $w(\theta | \overline{X})$, the posterior density of a parameter $\theta$ given the mean $\overline{X}$ of the data rather than the full data set. Here we show that $w(\theta | \overline{X})$ is asymptotically normal in an $L^1$ sense, and we identify the mean of the limiting normal and its asymptotic variance. The main results are first proved assuming that $X_1, \dots, X_n, \dots$ are independent and identical; suitable modifications to obtain results for the nonidentical case are given separately. Our results may be used to construct approximate HPD (highest posterior density) sets for the parameter which is of use in the statistical theory of standardized educational tests. They may also be used to show the covariance between two test items conditioned on the mean is asymptotically nonpositive. This has implications for constructing tests of item independence.

Article information

Ann. Statist., Volume 23, Number 6 (1995), 2116-2144.

First available in Project Euclid: 15 October 2002

Permanent link to this document

Digital Object Identifier

Mathematical Reviews number (MathSciNet)

Zentralblatt MATH identifier

Primary: 62F15: Bayesian inference
Secondary: 62E20: Asymptotic distribution theory

Asymptotic normality posterior educational testing sample mean


Clarke, B.; Ghosh, J. K. Posterior convergence given the mean. Ann. Statist. 23 (1995), no. 6, 2116--2144. doi:10.1214/aos/1034713650.

Export citation


  • ACKERMAN, T. A. 1991. An examination of the effect of multidimensionality on parallel forms construction. Presented at the Annual Meeting of the National Council on Measurement in Education, Chicago. Z.
  • BARTHOLOMEW, D. J. 1987. Latent Variable Models and Factor Analy sis. Oxford Univ. Press. Z.
  • BHATTACHARy A, R. N. and RAO, R. R. 1986. Normal Approximation and Asy mptotic Expansions. Krieger, Malabar. Z.
  • BICKEL, P. and YAHAV, J. 1969. Some contributions to the asy mptotic theory of Bay es' solutions. Z. Wahrsch. Verw. Gebeite 11 257 276. Z.
  • DOKSUM, K. A. and LO, A. Y. 1990. Consistent and robust Bay es procedures for location based on partial information. Ann. Statist. 18 443 453. Z.
  • HAMBLETON, R. K. 1989. Principles and selected applications of item response theory. In Z. Educational Measurement, 3rd ed. R. L. Linn, ed. 147 200. MacMillan, New York. Z.
  • HOLLAND, P. W. 1991. Private communication. Z.
  • IBRAGIMOV, I. A. and HASMINSKII, R. Z. 1981. Statistical Estimation. Springer, New York. Z. JOAG-DEV, K. and PROSCHAN, F. 1983. Negative association of random variables, with applications. Ann. Statist. 11 286 295. Z.
  • JUNKER, B. W. 1993. Conditional association, essential independence, and monotone unidimensional item response models. Ann. Statist. 21 1359 1378. Z.
  • LE CAM, L. 1953. On some asy mptotic properties of maximum likelihood estimates and related Bay es estimates. University of California Publications in Statistics 1 277 330. Z.
  • LE CAM, L. 1958. Les proprietes asy mptotiques des solution de Bay es. Publ. Inst. Statist. Univ. Paris 7 18 35.
  • LINDSAY, B., CLOGG, C. and GREGO, J. 1991. Semiparametric estimation in the Rasch model and related exponential response models, including a simple latent class model for item analysis. J. Amer. Statist. Assoc. 86 96 107. Z.
  • LORD, F. M. 1980. Application of Item Response Theory to Practical Testing Problems. Erlbaum, Hillsdale, NJ. Z.
  • TSUTAKAWA, R. K. and JOHNSON, J. C. 1990. The effect of uncertainty of item parameter estimation on ability estimates. Psy chometrika 55 371 390. Z.
  • TSUTAKAWA, R. K. and SOLTy S, M. J. 1990. Approximation for Bayesian ability estimation. Journal of Educational Statistics 13 117 130. Z.
  • WALKER, A. M. 1969. On the asy mptotic behavior of posterior distributions. J. Roy. Statist. Soc. Ser. B 31 80 88. Z.
  • YEN, W. M. 1984. Obtaining maximum likelihood estimates from number correct scores for the three parameter logistic model. Journal of Educational Measurement 21 93 112.