Second-order asymptotic expressions for the covariance matrix of maximum likelihood estimators in dispersion models

For the first time, we give an asymptotic formula of order n − 2 , where n is the sample size, for the covariance matrix of the maximum likelihood estimators of the regression parameters in regular dispersion models. The covariance matrix formula does not involve cumulants of log-likelihood derivati...

Full description

Saved in:
Bibliographic Details
Published in:Statistics & probability letters 2010-04, Vol.80 (7), p.718-725
Main Authors: Rocha, Andréa V., Simas, Alexandre B., Cordeiro, Gauss M.
Format: Article
Language:English
Subjects:
Exact sciences and technology
General topics
Mathematics
Probability and statistics
Probability theory and stochastic processes
Sampling theory, sample surveys
Sciences and techniques of general use
Statistics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:For the first time, we give an asymptotic formula of order n − 2 , where n is the sample size, for the covariance matrix of the maximum likelihood estimators of the regression parameters in regular dispersion models. The covariance matrix formula does not involve cumulants of log-likelihood derivatives and is very suitable for computer implementation. The formula yields expressions as special cases for the proper dispersion and exponential family nonlinear models. In particular, it extends the expression obtained by Cordeiro (2004) and corrects a result due to Cordeiro and Santana (2008). Some simulation results are also presented.
ISSN:0167-7152
1879-2103
DOI:10.1016/j.spl.2009.12.030