Nozer D. Singpurwalla

James S. Hodges

Robert E. Kass

Constantine Gatsonis

Robert E. McCulloch

Peter Rossi

This third volume of case studies presents detailed applications of Bayesian statistical analysis, emphasising the scientific context. The papers were presented and discussed at a workshop held at Carnegie-Mellon University, and this volume - dedicated to the memory of Morrie Groot-reproduces six invited papers, each with accompanying invited discussion, and nine contributed papers with the focus on econometric applications.

Volume III

Case Studies in Bayesian Statistics

The past few years have witnessed dramatic advances in computational methods for Bayesian inference. As a result, Bayesian approaches to solving a wide variety of problems in data analysis and decision-making have become feasible, and there is currently a growth spurt in the application of Bayesian methods. The purpose of this volume is to present several detailed examples of applications of Bayesian thinking, with an emphasis on the scientific or technological context of the problem being solved. The papers collected here were presented and discussed at a Workshop held at Carnegie-Mellon University, September 29 through October 1, 1991. There are five ma jor articles, each with two discussion pieces and a reply. These articles were invited by us following a public solicitation of abstracts. The problems they address are diverse, but all bear on policy decision-making. Though not part of our original design for the Workshop, that commonality of theme does emphasize the usefulness of Bayesian meth ods in this arena. Along with the invited papers were several additional commentaries of a general nature; the first comment was invited and the remainder grew out of the discussion at the Workshop. In addition there are nine contributed papers, selected from the thirty-four presented at the Workshop, on a variety of applications. This collection of case studies illustrates the ways in which Bayesian methods are being incorporated into statistical practice. The strengths (and limitations) of the approach become apparent through the examples.

A First Step toward a Unified Theory of Richly Parameterized Linear Models Using mixed linear models to analyze data often leads to results that are mysterious, inconvenient, or wrong. Further compounding the problem, statisticians lack a cohesive resource to acquire a systematic, theory-based understanding of models with random effects. Richly Parameterized Linear Models: Additive, Time Series, and Spatial Models Using Random Effects takes a first step in developing a full theory of richly parameterized models, which would allow statisticians to better understand their analysis results. The author examines what is known and unknown about mixed linear models and identifies research opportunities. The first two parts of the book cover an existing syntax for unifying models with random effects. The text explains how richly parameterized models can be expressed as mixed linear models and analyzed using conventional and Bayesian methods. In the last two parts, the author discusses oddities that can arise when analyzing data using these models. He presents ways to detect problems and, when possible, shows how to mitigate or avoid them. The book adapts ideas from linear model theory and then goes beyond that theory by examining the information in the data about the mixed linear model’s covariance matrices. Each chapter ends with two sets of exercises. Conventional problems encourage readers to practice with the algebraic methods and open questions motivate readers to research further. Supporting materials, including datasets for most of the examples analyzed, are available on the author’s website.

James S. Hodges

About

Books

Join the club