The statistical bias of numerically integrated statistical procedures

DOI10.1016/0898-1221(85)90041-0MaRDI QIDQ1070711zbMATH OpenOpenAlexFDO

Authors John Scott Butler

Publication date 1985

Published in Computers & Mathematics with Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0898-1221(85)90041-0

zbMATH Keywords

Bayesian posterior density functionsbiasesMaximum likelihood estimationmultivariate normal models

Mathematics Subject Classification ID

Point estimation (62F10) Estimation in multivariate analysis (62H12) Probabilistic methods, stochastic differential equations (65C99) Numerical integration (65D30)

Review text

Maximum likelihood estimation of multivariate normal models and Bayesian posterior density functions can require calculation using numerical integration. Although the statistical theory is unchanged for nonanalytical integrals, the exorbitant cost of estimating such models frequently induces researchers to use a small number of integration points. If the number of points is insufficient to calculate essentially exact values of the function being maximized, the resulting estimators are asymptotically biased and inconsistent both for the values of the estimated parameters and for their variances. The forms of the biases are derived and described in this paper.

Recommendations

• A Theory of Statistical Models for Monte Carlo Integration
• Bayesian computational methods
• Publication:3197188
• Corrections for Bias in Maximum Likelihood Parameter Estimates Due to Nuisance Parameters
• Biases in maximum simulated likelihood estimation of bivariate models

Cites work

• A Computationally Efficient Quadrature Procedure for the One-Factor Multinomial Probit Model
• scientific article; zbMATH DE number 3273551 (Why is no real title available?)
• scientific article; zbMATH DE number 3350922 (Why is no real title available?)
• scientific article; zbMATH DE number 3361229 (Why is no real title available?)
• scientific article; zbMATH DE number 3390199 (Why is no real title available?)
• scientific article; zbMATH DE number 3407003 (Why is no real title available?)

Cited in

(2)

• A comparison of different methods for the estimation of regression models with correlated binary responses.
• A mixed approach for the estimation of probit models with correlated responses: some finite sample results

This page was built for publication: The statistical bias of numerically integrated statistical procedures

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1070711)