Hierarchical Modelling for the Environmental Sciences Statistical Methods and Applications

by Clark, James S.; Gelfand, Alan

• ISBN13: 9780198569671
• ISBN10: 019856967X
• Format: Paperback
• Copyright: 2006-06-29
• Publisher: Oxford University Press

Summary

New statistical tools are changing the ways in which scientists analyze and interpret data and models. Many of these are emerging as a result of the wide availability of inexpensive, high speed computational power. In particular, hierarchical Bayes and Markov Chain Monte Carlo methods for anyalsis provide consistent framework for inference and prediction where information is heterogeneous and uncertain, processes are complex, and responses depend on scale. Nowhere are these methods more promising than in the environmental sciences. Models have developed rapidly, and there is now a requirement for a clear exposition of the methodology through to application for a range of environmental challenges.

Author Biography

James Clark is the Blomquist Professor at Duke University, where his research focuses on how global change affects forests and grasslands. He received a B.S. from the North Carolina State University in Entomology (1979), a M.S. from the University of Massachusetts in Forestry and Wildlife (1984), and a Ph.D. from the University of Minnesota in Ecology (1988). At Duke University, Clark teaches Community Ecology and Ecological Models & Data. He has served as the Director of Graduate Studies for the University Program in Ecology and as Director of the Center on Global Change. Alan E. Gelfand is the J B Duke Professor of Statistics and Decision Sciences at Duke University. An early contributor to the development of computational machinery for fitting hierarchical Bayesian models, his current research focuses on the analysis of spatial and spatio-temporal data. His primary areas of application are to problems in environmental science, ecology, and climatology. He received a B.S. from the City College of New York and an M.S. and Ph.D. from Stanford University. After many years at the University of Connecticut, he joined the faculty at Duke University in August 2002.

Table of Contents

Preface	v
Contributors	ix
Part I Introduction to hierarchical modeling	1	(38)
Elements of hierarchical Bayesian inference	3	(22)
Bradley P. Carlin
James S. Clark
Alan E. Gelfand
Bayesian hierarchical models in geographical genetics	25	(14)
Kent E. Holsinger
Part II Hierarchical models in experimental settings	39	(36)
Synthesizing ecological experiments and observational data with hierarchical Bayes	41	(18)
James S. Clark
Shannon LaDeau
Effects of global change on inflorescence production: a Bayesian hierarchical analysis	59	(16)
Janneke Hille Ris Lambers
Brian Aukema
Jeff Diez
Margaret Evans
Andrew Latimer
Part III Spatial modeling	75	(44)
Building statistical models to analyze species distributions	77	(21)
Alan E. Gelfand
Andrew Latimer
Shanshan Wu
John A. Silander, Jr
Implications of vulnerability to hurricane damage for long-term survival of tropical tree species: a Bayesian hierarchical analysis	98	(21)
Kiona Ogle
Maria Uriarte
Jill Thompson
Jill Johnstone
Andy Jones
Yiching Lin
Eliot J. B. McIntire
Jess K. Zimmerman
Part IV Spatio-temporal modeling	119	(66)
Spatial-temporal statistical modeling and prediction of environmental processes	121	(24)
Li Chen
Montserrat Fuentes
Jerry M. Davis
Hierarchical Bayesian spatio-temporal models for population spread	145	(25)
Christopher K. Wikle
Mevin B. Hooten
Spatial models for the distribution of extremes	170	(15)
Eric Gilleland
Douglas Nychka
Uli Schneider
References	185	(12)
Index	197