Constrained Statistical Inference: Order, Inequality, and Shape Constraints

Mervyn J. Silvapulle

ISBN 10: 0471208272 / ISBN 13: 9780471208273

Editore: John Wiley & Sons Inc, 2004

Riguardo questo articolo

This item is printed on demand. New copy - Usually dispatched within 5-9 working days 930. Codice articolo C9780471208273

Dati bibliografici

Titolo: Constrained Statistical Inference: Order, ...

Casa editrice: John Wiley & Sons Inc

Data di pubblicazione: 2004

Legatura: Hardback

Condizione: New

Descrizione articolo

Riassunto:

An up-to-date approach to understanding statistical inference

Statistical inference is finding useful applications in numerous fields, from sociology and econometrics to biostatistics. This volume enables professionals in these and related fields to master the concepts of statistical inference under inequality constraints and to apply the theory to problems in a variety of areas.

Constrained Statistical Inference: Order, Inequality, and Shape Constraints provides a unified and up-to-date treatment of the methodology. It clearly illustrates concepts with practical examples from a variety of fields, focusing on sociology, econometrics, and biostatistics.

The authors also discuss a broad range of other inequality-constrained inference problems that do not fit well in the contemplated unified framework, providing a meaningful way for readers to comprehend methodological resolutions.

Chapter coverage includes:

• Population means and isotonic regression
• Inequality-constrained tests on normal means
• Tests in general parametric models
• Likelihood and alternatives
• Analysis of categorical data
• Inference on monotone density function, unimodal density function, shape constraints, and DMRL functions
• Bayesian perspectives, including Stein’s Paradox, shrinkage estimation, and decision theory

Recensione:

"This monograph provides an excellent coverage of the last twenty years of constrained statistical inference." ( Journal of the American Statistical Association, March 2006)

" an invaluable resource for any researcher with interests in constrained problems it is easy to conclude that any statistical library would be incomplete without it." (Biometrics, December 2005)

" a valuable source of information for statisticians working in any area " (Mathematical Reviews, 2005k)