Clarke, B. ; Ghosh, J. K. (1995) Posterior convergence given the mean Annals of Statistics, 23 (6). pp. 21162144. ISSN 00905364

PDF
 Publisher Version
459kB 
Official URL: http://www.jstor.org/pss/2242788
Abstract
For various applications one wants to know the asymptotic behavior of ω (θX^{}), the posterior density of a parameter θ given the mean X^{} of the data rather than the full data set. Here we show that ω (θX^{}) 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},...,X_{n},... 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.
Item Type:  Article 

Source:  Copyright of this article belongs to Institute of Mathematical Statistics. 
ID Code:  22653 
Deposited On:  24 Nov 2010 08:04 
Last Modified:  17 May 2016 06:39 
Repository Staff Only: item control page