Muutke küpsiste eelistusi

Flexible Bayesian Regression Modelling [Pehme köide]

Edited by (University of Melbourne, Australia), Edited by (National University of Singapore), Edited by (Institut de Recherche Mathematique Avancee, France), Edited by (University of New South Wales, Sydney, Australia)
  • Formaat: Paperback / softback, 302 pages, kõrgus x laius: 229x152 mm, kaal: 480 g
  • Ilmumisaeg: 31-Oct-2019
  • Kirjastus: Academic Press Inc
  • ISBN-10: 012815862X
  • ISBN-13: 9780128158623
Teised raamatud teemal:
Flexible Bayesian Regression ModellingSuurem pilt
  • Formaat: Paperback / softback, 302 pages, kõrgus x laius: 229x152 mm, kaal: 480 g
  • Ilmumisaeg: 31-Oct-2019
  • Kirjastus: Academic Press Inc
  • ISBN-10: 012815862X
  • ISBN-13: 9780128158623
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9780128158623.html
Märksõnad:

Flexible Bayesian Regression Modeling is a step-by-step guide to the Bayesian revolution in regression modeling, for use in advanced econometric and statistical analysis where datasets are characterized by complexity, multiplicity, and large sample sizes, necessitating the need for considerable flexibility in modeling techniques. It reviews three forms of flexibility: methods which provide flexibility in their error distribution; methods which model non-central parts of the distribution (such as quantile regression); and finally models that allow the mean function to be flexible (such as spline models). Each chapter discusses the key aspects of fitting a regression model. R programs accompany the methods.

This book is particularly relevant to non-specialist practitioners with intermediate mathematical training seeking to apply Bayesian approaches in economics, biology, finance, engineering and medicine.

  • Introduces powerful new nonparametric Bayesian regression techniques to classically trained practitioners
  • Focuses on approaches offering both superior power and methodological flexibility
  • Supplemented with instructive and relevant R programs within the text
  • Covers linear regression, nonlinear regression and quantile regression techniques
  • Provides diverse disciplinary case studies for correlation and optimization problems drawn from Bayesian analysis ‘in the wild’

Arvustused

Flexible Bayesian Regression Modelling is a step-by-step guide to the Bayesian revolution in regression modelling, for use in advanced econometric and statistical analysis where datasets are characterized by complexity, multiplicity, and large sample sizes, necessitating the need for considerable flexibility in modelling techniques." --Mathematical Reviews Clippings

Contributors ix
Preface xiii
1 Bayesian quantile regression with the asymmetric Laplace distribution
1(26)
J.-L. Dortet-Bernadet
Y. Fan
T. Rodrigues
1.1 Introduction
1(2)
1.2 The asymmetric Laplace distribution for quantile regression
3(13)
1.3 On coverage probabilities
16(2)
1.4 Postprocessing for multiple fittings
18(4)
1.5 Final remarks and conclusion
22(1)
References
23(4)
2 A vignette on model-based quantile regression: analysing excess zero response
27(38)
Erika Cunningham
Surya T. Tokdar
James S. Clark
2.1 Introduction
28(2)
2.2 Excess zero regression analysis
30(1)
2.3 Case study data and objective
31(1)
2.4 Fitting single covariate basal area models
32(5)
2.5 Interpreting quantile regressions
37(4)
2.6 Assessing model assumptions and making improvements
41(6)
2.7 Prediction and interpreting predicted responses
47(3)
2.8 Fitting multiple regression basal area models
50(12)
2.9 Conclusions and final remarks
62(1)
Acknowledgement
63(1)
References
63(2)
3 Bayesian nonparametric density regression for ordinal responses
65(26)
Maria DeYoreo
Athanasios Kottas
3.1 Introduction
65(3)
3.2 Bayesian nonparametric density regression
68(5)
3.3 Mixture modelling for ordinal responses
73(13)
3.4 Summary
86(1)
Acknowledgements
87(1)
References
87(4)
4 Bayesian non para metric methods for financial and macroeconomic time series analysis
91(30)
Maria Kalli
4.1 Introduction
91(2)
4.2 Bayesian nonparametric methods for the innovation distribution in volatility models
93(5)
4.3 Bayesian nonparametric methods for long-range dependence in SV models
98(7)
4.4 Bayesian nonparametric methods for the analysis of macroeconomic time series
105(9)
4.5 Conclusion
114(1)
References
115(6)
5 Bayesian mixed binary-continuous copula regression with an application to childhood undernutrition
121(32)
Nadja Klein
Thomas Kneib
Giampiero Marra
Rosalba Radice
5.1 Introduction
121(4)
5.2 Bivariate copula models with mixed binary-continuous marginals
125(7)
5.3 Bayesian inference
132(6)
5.4 Model selection and model evaluation
138(4)
5.5 Results
142(5)
5.6 Summary and discussion
147(2)
Acknowledgements
149(1)
References
149(4)
6 Nonstandard flexible regression via variational Bayes
153(34)
John T. Ormerod
6.1 Introduction
154(2)
6.2 Preparatory modelling components
156(7)
6.3 A standard semiparametric regression model
163(2)
6.4 Robust nonparametric regression
165(5)
6.5 Generalised additive model with heteroscedastic variance
170(3)
6.6 Generalised additive negative binomial model
173(4)
6.7 Logistic regression with missing covariates
177(5)
6.8 Conclusion
182(1)
Acknowledgements
183(1)
References
183(4)
7 Scalable Bayesian variable selection regression models for count data
187(34)
Yinsen Miao
Jeong Hwan Kook
Yadong Lu
Michele Guindani
Marina Vannucci
7.1 Introduction
188(1)
7.2 Bayesian variable selection via spike-and-slab priors
189(1)
7.3 Negative binomial regression models
190(10)
7.4 Dirichlet-multinomial regression models
200(6)
7.5 Simulation study
206(6)
7.6 Benchmark applications
212(3)
7.7 Conclusion
215(1)
References
216(5)
8 Bayesian spectral analysis regression
221(30)
Taeryon Choi
Peter J. Lenk
8.1 Introduction
221(2)
8.2 Smooth operators
223(4)
8.3 Bayesian spectral analysis regression
227(7)
8.4 Shape constraints
234(3)
8.5 Nonnormal distributions
237(1)
8.6 R library bsamGP
238(7)
8.7 Conclusion
245(1)
Acknowledgements
246(1)
References
246(5)
9 Flexible regression modelling under shape constraints
251(30)
Andrew A. Manderson
Kevin Murray
Berwin A. Turlach
9.1 Introduction
252(1)
9.2 Orthonormal design matrices
253(1)
9.3 Monotonic polynomial model
254(7)
9.4 Covariate selection
261(17)
9.5 Conclusion
278(1)
References
278(3)
Index 281
Dr. Yanan Fan is Associate Professor of statistics at the University of New South Wales, Sydney, Australia. Her research focuses on the development of efficient Bayesian computational methods, approximate inferences and nonparametric regression methods. Dr. David Nott is Associate Professor of Statistics at the National University of Singapore. His research focuses on Bayesian likelihood-free inference and other approximate inference methods, and on complex Bayesian nonparametric models. Dr. Michael Stanley Smith is Professor of Management (Econometrics) at Melbourne Business School, University of Melbourne, as well as Honorary Professor of Business Analytics at the University of Sydney. Michaels research is in developing Bayesian models and methods, and applying them to problems that arise in business, economics and elsewhere. Dr. Jean-Luc Dortet-Bernadet is maître de conférences at the Université de Strasbourg, France, and member of the Institut de Recherche Mathématique Avancée (IRMA). His research focuses mainly on the development of some Bayesian methods, nonparametric methods and on the study of dependence.