Maximum Entropy Approximations for Asymptotic Distributions of Smooth Functions of Sample Means Academic Article

abstract

• We propose an information-theoretic approach to approximate asymptotic distributions of statistics using the maximum entropy (ME) densities. Conventional ME densities are typically defined on a bounded support. For distributions defined on unbounded supports, we use an asymptotically negligible dampening function for the ME approximation such that it is well defined on the real line. We establish order n-1 asymptotic equivalence between the proposed method and the classical Edgeworth approximation for general statistics that are smooth functions of sample means. Numerical examples are provided to demonstrate the efficacy of the proposed method. 2010 Board of the Foundation of the Scandinavian Journal of Statistics.

authors

• Wu, Ximing

published proceedings

• SCANDINAVIAN JOURNAL OF STATISTICS

author list (cited authors)

• Wu, X., & Wang, S.

citation count

• 1

complete list of authors

• Wu, Ximing||Wang, Suojin

publication date

• March 2011

publisher

• Wiley  Publisher

published in

• Scandinavian Journal of Statistics: theory and applications  Journal

keywords

• Asymptotic Approximation
• Edgeworth Approximation
• Maximum Entropy Density

Digital Object Identifier (DOI)

• 10.1111/j.1467-9469.2010.00698.x

start page

• 130

end page

• 146

volume

• 38

issue

• 1

URL

• http://dx.doi.org/10.1111/j.1467-9469.2010.00698.x