Skip Navigation
List Price: $61.26

Rent Textbook

Select for Price
Add to Cart Free Shipping
There was a problem. Please try again later.

New Textbook

We're Sorry
Sold Out

Used Textbook

We're Sorry
Sold Out

Discrete Choice Methods With Simulation,9780521747387

Discrete Choice Methods With Simulation

Edition: 2nd
Format: Paperback
Pub. Date: 6/30/2009
Publisher(s): Cambridge University Press
Availability: This title is currently not available.


This book describes the new generation of discrete choice methods, focusing on the many advances that are made possible by simulation. Researchers use these statistical methods to examine the choices that consumers, households, firms, and other agents make. Each of the major models is covered: logit, generalized extreme value, or GEV (including nested and cross-nested logits), probit, and mixed logit, plus a variety of specifications that build on these basics. Simulation-assisted estimation procedures are investigated and compared, including maximum stimulated likelihood, method of simulated moments, and method of simulated scores. Procedures for drawing from densities are described, including variance reduction techniques such as anithetics and Halton draws. Recent advances in Bayesian procedures are explored, including the use of the Metropolis-Hastings algorithm and its variant Gibbs sampling. The second edition adds chapters on endogeneity and expectation-maximization (EM) algorithms. No other book incorporates all these fields, which have arisen in the past 25 years. The procedures are applicable in many fields, including energy, transportation, environmental studies, health, labor, and marketing.

Author Biography

Professor Kenneth E. Train teaches econometrics, regulation, and industrial organization at the University of California, Berkeley. He also serves as Vice President of National Economic Research Associates (NERA), Inc., in San Francisco, California. The author of Optimal Regulation: The Economic Theory of Natural Monopoly (1991) and Qualitative Choice Analysis (1986), Dr. Train has written more than 60 articles on economic theory and regulation. He chaired the Center for Regulatory Policy at the University of California, Berkeley, from 1993 to 2000 and has testified as an expert witness in regulatory proceedings and court cases. He has received numerous awards for his teaching and research.

Table of Contents

Introductionp. 1
Motivationp. 1
Choice Probabilities and Integrationp. 3
Outline of Bookp. 7
A Couple of Notesp. 8
Behavioral Models
Properties of Discrete Choice Modelsp. 11
Overviewp. 11
The Choice Setp. 11
Derivation of Choice Probabilitiesp. 14
Specific Modelsp. 17
Identification of Choice Modelsp. 19
Aggregationp. 29
Forecastingp. 32
Recalibration of Constantsp. 33
Logitp. 34
Choice Probabilitiesp. 34
The Scale Parameterp. 40
Power and Limitations of Logitp. 42
Nonlinear Representative Utilityp. 52
Consumer Surplusp. 55
Derivatives and Elasticitiesp. 57
Estimationp. 60
Goodness of Fit and Hypothesis Testingp. 67
Case Study: Forecasting for a New Transit Systemp. 71
Derivation of Logit Probabilitiesp. 74
GEVp. 76
Introductionp. 76
Nested Logitp. 77
Three-Level Nested Logitp. 86
Overlapping Nestsp. 89
Heteroskedastic Logitp. 92
The GEV Familyp. 93
Probitp. 97
Choice Probabilitiesp. 97
Identificationp. 100
Taste Variationp. 106
Substitution Patterns and Failure of IIAp. 108
Panel Datap. 110
Simulation of the Choice Probabilitiesp. 114
Mixed Logitp. 134
Choice Probabilitiesp. 134
Random Coefficientsp. 137
Error Componentsp. 139
Substitution Patternsp. 141
Approximation to Any Random Utility Modelp. 141
Simulationp. 144
Panel Datap. 145
Case Studyp. 147
Variations on a Themep. 151
Introductionp. 151
Stated-Preference and Revealed-Preference Datap. 152
Ranked Datap. 156
Ordered Responsesp. 159
Contingent Valuationp. 164
Mixed Modelsp. 166
Dynamic Optimizationp. 169
Numerical Maximizationp. 185
Motivationp. 185
Notationp. 185
Algorithmsp. 187
Convergence Criterionp. 198
Local versus Global Maximump. 199
Variance of the Estimatesp. 200
Information Identityp. 202
Drawing from Densitiesp. 205
Introductionp. 205
Random Drawsp. 205
Variance Reductionp. 214
Simulation-Assisted Estimationp. 237
Motivationp. 237
Definition of Estimatorsp. 238
The Central Limit Theoremp. 245
Properties of Traditional Estimatorsp. 247
Properties of Simulation-Based Estimatorsp. 250
Numerical Solutionp. 257
Individual-Level Parametersp. 259
Introductionp. 259
Derivation of Conditional Distributionp. 262
Implications of Estimation of $$p. 264
Monte Carlo Illustrationp. 267
Average Conditional Distributionp. 269
Case Study: Choice of Energy Supplierp. 270
Discussionp. 280
Bayesian Proceduresp. 282
Introductionp. 282
Overview of Bayesian Conceptsp. 284
Simulation of the Posterior Meanp. 291
Drawing from the Posteriorp. 293
Posteriors for the Mean and Variance of a Normal Distributionp. 294
Hierarchical Bayes for Mixed Logitp. 299
Case Study: Choice of Energy Supplierp. 305
Bayesian Procedures for Probit Modelsp. 313
Endogeneityp. 315
Overviewp. 315
The BLP Approachp. 318
Supply Sidep. 328
Control Functionsp. 334
Maximum Likelihood Approachp. 340
Case Study: Consumers' Choice among New Vehiclesp. 342
EM Algorithmsp. 347
Introductionp. 347
General Procedurep. 348
Examples of EM Algorithmsp. 355
Case Study: Demand for Hydrogen Carsp. 365
Bibliographyp. 371
Indexp. 385
Table of Contents provided by Ingram. All Rights Reserved.

An electronic version of this book is available through VitalSource.

This book is viewable on PC, Mac, iPhone, iPad, iPod Touch, and most smartphones.

By purchasing, you will be able to view this book online, as well as download it, for the chosen number of days.

A downloadable version of this book is available through the eCampus Reader or compatible Adobe readers.

Applications are available on iOS, Android, PC, Mac, and Windows Mobile platforms.

Please view the compatibility matrix prior to purchase.

American Express