# An introduction to bayesian inference in econometrics / Arnold Zellner

##### By: Zellner, Arnold [autor]

Publisher: New York, United States : John Wiley & Sons, ©1971Description: 431 páginas : ilustraciones, tablas ; 24 cmContent type: Media type: Carrier type: ISBN: 0471981656Subject(s): Análisis de Regresión | Analisis de Series de Tiempo | Diseño experimental | Econometria | Ecuaciones SimultaneasDDC classification: 330.015195Item type | Current location | Collection | Call number | Vol info | Copy number | Status | Date due | Barcode | Item holds |
---|---|---|---|---|---|---|---|---|---|

Book | B. Campus los Cerros Colección general | Colección general | 330.015195 Z51 (Browse shelf) | 1971 | 1 | Available | 0000042318 |

#### Enhanced descriptions from Syndetics:

This is a classical reprint edition of the original 1971 edition ofAn Introduction to Bayesian Inference in Economics. This historical volume is an early introduction to Bayesian inference and methodology which still has lasting value for today's statistician and student. The coverage ranges from the fundamental concepts and operations of Bayesian inference to analysis of applications in specific econometric problems and the testing of hypotheses and models.

Includes appendix, bibliography and index. -- Appendix A. -- Appendix B. -- Appendix C.

Remarks on inference in economics. -- The unity of science. -- Deductive inference. -- Inductive inference. -- Principles of Bayesian analysis with selected applications. -- Bayes' theorem. -- Bayes' theorem and several sets of data. -- Prior probability density functions. -- The univariate normal linear regression model. -- the simple univariate normal linear regression model. -- Model and likelihood function. -- Posterior PDF'S for parameters with a diffuse prior PDF. -- The normal multiple regression model. -- Special problems in regression analysis. -- The regression model with auto correlated errors. -- Regression with unequal variances. -- Two regressions with some common coefficients. -- On errors in the variables. -- The classical EVM: Preliminary problem. -- Classical EVM: Analysis of the functional form. -- ML Analysis of structural form of the EVM. -- Analysis of single equation nonlinear Models. -- The box - cox analysis of transformations. -- Constant elasticity of substitution (CES) production. -- Generalized production functions. -- Time series models: some selected examples. -- First order normal auto regressive process. -- First order autoregressive model with incomplete data. -- Analysis of second order autoregressive process. -- Multivariate regression models. -- The traditional multivariate regression models. -- Predictive PDF for the traditional Regression model. -- The traditional multivariate model with exact restrictions. -- Simultaneous equation econometric models. -- fully recursive models. -- General triangular systems. -- The concept of identification in Bayesian analysis. -- On comparing and testing hypotheses. -- Posterior probabilities associated with hypotheses. -- Analyzing hypotheses with diffuse prior PDF'S for parameters.

The purpose of this book is to provide readers with an introduction to Bayesian inference in econometrics. An effort has been made to relate the problems of inference in econometrics to the general problems of inference in science and to indicate how the Bayesian approach relates to general problems of scientific inference in chapter I. In chapter II some fundamental concepts and operations employed in the Bayesian approach o inference are presented, discussed, and applied in analyses of several simple and important problems. Chapter III through IX are devoted to Bayesian analyses of models often encountered in econometric work, with sampling theory results are made. In chapter X I treat the problems of testing and comparing hypotheses, and in chapter XI I analyze several control problems relating to regression and other processes. In chapter XII I presented some concluding remarks. Appendices A and B provide a resume of the properties of a number of important univariate and multivariate distributions. In appendix C univariate and bivariate numerical integration techniques ae briefly described. I have tried to keep the analysis and notation in this book as simple as possible. However, readers are assumed to be familiar with basic concepts and operations of probability theory, differential and integral calculus and matrix algebra.

There are no comments for this item.