DMCA
Monte Carlo Computation of the Fisher Information Matrix in Nonstandard Settings
| Citations: | 9 - 2 self |
BibTeX
@MISC{Spall_montecarlo,
author = {James C. Spall},
title = {Monte Carlo Computation of the Fisher Information Matrix in Nonstandard Settings},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The Fisher information matrix summarizes the amount of information in the data relative to the quantities of interest. There are many applications of the information matrix in modeling, systems analysis, and estimation, including confidence region calculation, input design, prediction bounds, and “noninformative ” priors for Bayesian analysis. This article reviews some basic principles associated with the information matrix, presents a resamplingbased method for computing the information matrix together with some new theory related to efficient implementation, and presents some numerical results. The resampling-based method relies on an efficient technique for estimating the Hessian matrix, introduced as part of the adaptive (“second-order”) form of the simultaneous perturbation stochastic approximation (SPSA) optimization algorithm. Key Words: Antithetic random numbers; Cramér-Rao bound; Hessian matrix estimation; Monte Carlo simulation; Simultaneous perturbation (SP).
Keyphrases
fisher information matrix monte carlo computation information matrix nonstandard setting simultaneous perturbation input design data relative simultaneous perturbation stochastic approximation resampling-based method relies cram r-rao bound key word hessian matrix prediction bound efficient technique resamplingbased method efficient implementation new theory bayesian analysis numerical result basic principle hessian matrix estimation noninformative prior antithetic random number monte carlo simulation system analysis confidence region calculation many application optimization algorithm
