Bayesian Full Information Analysis of Simultaneous Equation Models Using Integration by Monte Carlo
Published on 1. September 1984
Book
Paperback/Softback
VI, 114 pages
978-3-540-13384-1 (ISBN)
Description
In their review of the "Bayesian analysis of simultaneous equation systems", Dr~ze and Richard (1983) - hereafter DR - express the following viewpoint about the present state of development of the Bayesian full information analysis of such sys tems i) the method allows "a flexible specification of the prior density, including well defined noninformative prior measures"; ii) it yields "exact finite sample posterior and predictive densities". However, they call for further developments so that these densities can be eval uated through 'numerical methods, using an integrated software packa~e. To that end, they recommend the use of a Monte Carlo technique, since van Dijk and Kloek (1980) have demonstrated that "the integrations can be done and how they are done". In this monograph, we explain how we contribute to achieve the developments suggested by Dr~ze and Richard. A basic idea is to use known properties of the porterior density of the param eters of the structural form to design the importance functions, i. e. approximations of the posterior density, that are needed for organizing the integrations.
More details
Series
Edition
Softcover reprint of the original 1st ed. 1984
Language
English
Place of publication
Berlin
Germany
Publishing group
Springer Berlin
Target group
Professional and scholarly
Research
Illustrations
VI, 114 p.
Dimensions
Height: 244 mm
Width: 170 mm
Thickness: 8 mm
Weight
236 gr
ISBN-13
978-3-540-13384-1 (9783540133841)
DOI
10.1007/978-3-642-45578-0
Schweitzer Classification
Content
I. The Statistical Model.- 1.1 Notation.- 1.2 Interpretation.- 1.3 Likelihood function.- II. Bayesian Inference: The Extended Natural-Conjugate Approach.- II.1 Two reformulations of the likelihood function.- II.2 The extended natural-conjugate prior density.- II.3 Posterior densities.- II.4 Predictive moments.- II.5 Numerical integration by importance sampling.- III. Selection of Importance Functions.- III.1 General criteria.- III.2 The AI (?) approach.- III.3 The AI(?) approach.- IV. Report and Discussion of Experiments.- IV.1 Report.- IV.2 Conclusions.- V. Extensions.- V.I Prior density.- V.2 Nonlinear Models.- Conclusion.- Appendix A: Density Functions: Definitions, Properties And Algorithms For Generating Random Drawings.- A.I The matricvariate normal (MN) distribution.- A.II The inverted-Wishart (iW) distribution.- A.III The multivariate Student distribution.- A.IV The 2-0 poly-t distribution.- A.V The m-1 (0 < m ? 2) poly-t distribution.- Appendix B: The Technicalities of Chapter III.- B.I Definition of the parameters of (3.3) and (3.6).- B.II Computation of the posterior mode of ?.- B.III Computation of (3.15).- Appendix C: Plots of Posterior Marginal Densities And of Importance Functions.- Appendix D: The Computer Program.- Footnotes.- References.