Bayesian Inference in the Social Sciences

ISBN-13: 9781118771211 / Angielski / Twarda / 2014 / 350 str.

Ivan Jeliazkov; Xin-She Yang

Opis

Bayesian Inference in the Social Sciences builds upon the recent growth in Bayesian methodology and examines an array of topics in model formulation, estimation, and applications. Particular emphasis is placed on an interdisciplinary coverage, model checking, and modern computational tools such as Markov chain Monte Carlo.

Spis treści

List of Figures iii

1 Bayesian Analysis of Dynamic Network Regression with Joint Edge/Vertex Dynamics 1
Zack W. Almquist and Carter T. Butts

1.1 Introduction 2

1.2 Statistical Models for Social Network Data 2

1.3 Dynamic Network Logistic Regression with Vertex Dynamics 11

1.4 Empirical Examples and Simulation Analysis 14

1.5 Discussion 29

1.6 Conclusion 30

2 Ethnic Minority Rule and Civil War: A Bayesian Dynamic Multilevel Analysis 39
Xun Pang

2.1 Introduction: Ethnic Minority Rule and Civil War 40

2.2 EMR: Grievance and Opportunities of Rebellion 41

2.3 Bayesian GLMM–AR(p) Model 42

2.4 Variables, Model and Data 47

2.5 Empirical Results and Interpretation 49

2.6 Civil War: Prediction 54

2.7 Robustness Checking: Alternative Measures of EMR 59

2.8 Conclusion 60

References 62

3 Bayesian Analysis of Treatment Effect Models 67
Mingliang Li and Justin L. Tobias

3.1 Introduction 68

3.2 Linear Treatment Response Models Under Normality 69

3.3 Nonlinear Treatment Response Models 73

3.4 Other Issues and Extensions: Non–Normality, Model Selection and Instrument Imperfection 78

3.5 Illustrative Application 84

3.6 Conclusion 89

4 Bayesian Analysis of Sample Selection Models 95
Martijn van Hasselt

4.1 Introduction 95

4.2 Univariate Selection Models 97

4.3 Multivariate Selection Models 101

4.4 Semiparametric Models 111

4.5 Conclusion 114

References 114

5 Modern Bayesian Factor Analysis 117
Hedibert Freitas Lopes

5.1 Introduction 117

5.2 Normal linear factor analysis 119

5.3 Factor stochastic volatility 125

5.4 Spatial factor analysis 128

5.5 Additional developments 133

5.6 Modern non–Bayesian factor analysis 136

5.7 Final remarks 137

6 Estimation of stochastic volatility models with heavy tails and serial dependence 159
Joshua C.C. Chan and Cody Y.L. Hsiao

6.1 Introduction 159

6.2 Stochastic Volatility Model 160

6.3 Moving Average Stochastic Volatility Model 168

6.4 Stochastic Volatility Models with Heavy–Tailed Error Distributions 173

References 178

7 From the Great Depression to the Great Recession: A Modelbased Ranking of U.S. Recessions 181
Rui Liu and Ivan Jeliazkov

7.1 Introduction 181

7.2 Methodology 183

7.3 Results 188

7.4 Conclusions 191

Appendix: Data 192

References 192

8 What Difference Fat Tails Make: A Bayesian MCMC Estimation of Empirical Asset Pricing Models 201
Paskalis Glabadanidis

8.1 Introduction 202

8.2 Methodology 204

8.3 Data 205

8.4 Empirical Results 206

8.5 Concluding Remarks 212

9 Stochastic Search For Price Insensitive Consumers 227
Eric Eisenstat

9.1 Introduction 228

9.2 Random utility models in marketing applications 230

9.3 The censored mixing distribution in detail 234

9.4 Reference price models with price thresholds 240

9.5 Conclusion 244

References 245

10 Hierarchical Modeling of Choice Concentration of US Households 249
Karsten T. Hansen, Romana Khan and Vishal Singh

10.1 Introduction 250

10.2 Data Description 252

10.3 Measures of Choice Concentration 252

10.4 Methodology 254

10.5 Results 256

10.6 Interpreting 260

10.7 Decomposing the effects of time, number of decisions and concentration preference 263

10.8 Conclusion 265

References 267

11 Approximate Bayesian inference in models defined through estimating equations 269

11.1 Introduction 269

11.2 Examples 271

11.3 Frequentist estimation 273

11.4 Bayesian estimation 276

11.5 Simulating from the posteriors 281

11.6 Asymptotic theory 283

11.7 Bayesian validity 285

11.8 Application 286

11.9 Conclusions 288

12 Reacting to Surprising Seemingly Inappropriate Results 295
Dale J. Poirier

12.1 Introduction 295

12.2 Statistical Framework 296

12.3 Empirical Illustration 300

12.4 Discussion 301

References 301

13 Identification and MCMC estimation of bivariate probit models with partial observability 303
Ashish Rajbhandari

13.1 Introduction 303

13.2 Bivariate Probit Model 305

13.3 Identification in a partially observable model 307

13.4 Monte Carlo Simulations 308

13.5 Bayesian Methodology 309

13.6 Application 312

13.7 Conclusion 315

Chapter Appendix 316

References 317

14 School Choice Effects in Tokyo Metropolitan Area: A Bayesian Spatial Quantile Regression Approach 321
Kazuhiko Kakamu and Hajime Wago

14.1 Introduction 321

14.2 The Model 323

14.3 Posterior Analysis 325

14.4 Empirical Analysis 326

14.5 Conclusions 330

O autorze

IVAN JELIAZKOV, PhD, is Associate Professor of Economics and Statistics at the University of California, Irvine. Dr. Jeliazkov s research interests include Bayesian econometrics and discrete data analysis, model comparison, and simulation–based inference. In addition to developing new methods and estimation techniques, his work features applications in a variety of disciplines, including micro– and macroeconomics, marketing, political science, transportation, and environmental engineering.

XIN–SHE YANG, PhD, is Reader in Modeling and Optimization at Middlesex University, United Kingdom, as well as Adjunct Professor at Reykjavik University, Iceland. He is the author of Mathematical Modeling with Multidisciplinary Applications and Engineering Optimization: An Introduction with Metaheuristic Applications, both of which are published by Wiley.

Blurb

Presents new models, methods, and techniques and considers important real–world applications in political science, sociology, economics, marketing, and finance

Emphasizing interdisciplinary coverage, Bayesian Inference in the Social Sciences builds upon the recent growth in Bayesian methodology and examines an array of topics in model formulation, estimation, and applications. The book presents recent and trending developments in a diverse, yet closely integrated, set of research topics within the social sciences and facilitates the transmission of new ideas and methodology across disciplines while maintaining manageability, coherence, and a clear focus.

Bayesian Inference in the Social Sciences features innovative methodology and novel applications in addition to new theoretical developments and modeling approaches, including the formulation and analysis of models with partial observability, sample selection, and incomplete data. Additional areas of inquiry include a Bayesian derivation of empirical likelihood and method of moment estimators, and the analysis of treatment effect models with endogeneity. The book emphasizes practical implementation, reviews and extends estimation algorithms, and examines innovative applications in a multitude of fields. Time series techniques and algorithms are discussed for stochastic volatility, dynamic factor, and time–varying parameter models. Additional features include:

• Real–world applications and case studies that highlight asset pricing under fat–tailed distributions, price indifference modeling and market segmentation, analysis of dynamic networks, ethnic minorities and civil war, school choice effects, and business cycles and macroeconomic performance
• State–of–the–art computational tools and Markov chain Monte Carlo algorithms with related materials available via the book s supplemental website
• Interdisciplinary coverage from well–known international scholars and practitioners

Bayesian Inference in the Social Sciences is an ideal reference for researchers in economics, political science, sociology, and business as well as an excellent resource for academic, government, and regulation agencies. The book is also useful for graduate–level courses in applied econometrics, statistics, mathematical modeling and simulation, numerical methods, computational analysis, and the social sciences.