This book is a full-scale exposition of Charles Manski's new methodology for analyzing empirical questions in the social sciences. He recommends that researchers first ask what can be learned from data alone, and then ask what can be learned when data are combined with credible weak assumptions. Inferences predicated on weak assumptions, he argues, can achieve wide consensus, while ones that require strong assumptions almost inevitably are subject to sharp disagreements. Building on the foundation laid in the author's Identification Problems in the Social Sciences (Harvard, 1995), the book's fifteen chapters are organized in three parts. Part I studies prediction with missing or otherwise incomplete data. Part II concerns the analysis of treatment response, which aims to predict outcomes when alternative treatment rules are applied to a population. Part III studies prediction of choice behavior. Each chapter juxtaposes developments of methodology with empirical or numerical illustrations. The book employs a simple notation and mathematical apparatus, using only basic elements of probability theory.

Manski argues that public policy is based on untrustworthy analysis. Failing to account for uncertainty in an uncertain world, policy analysis routinely misleads policy makers with expressions of certitude. Manski critiques the status quo and offers an innovation to improve both how policy research is conducted and how it is used by policy makers.

This text prepares first-year graduate students and advanced undergraduates for empirical research in economics, and also equips them for specialization in econometric theory, business, and sociology. A Course in Econometrics is likely to be the text most thoroughly attuned to the needs of your students. Derived from the course taught by Arthur S. Goldberger at the University of Wisconsin-Madison and at Stanford University, it is specifically designed for use over two semesters, offers students the most thorough grounding in introductory statistical inference, and offers a substantial amount of interpretive material. The text brims with insights, strikes a balance between rigor and intuition, and provokes students to form their own critical opinions. A Course in Econometrics thoroughly covers the fundamentals--classical regression and simultaneous equations--and offers clear and logical explorations of asymptotic theory and nonlinear regression. To accommodate students with various levels of preparation, the text opens with a thorough review of statistical concepts and methods, then proceeds to the regression model and its variants. Bold subheadings introduce and highlight key concepts throughout each chapter. Each chapter concludes with a set of exercises specifically designed to reinforce and extend the material covered. Many of the exercises include real microdata analyses, and all are ideally suited to use as homework and test questions.

The author draws on examples from a range of disciplines to provide social and behavioural scientists with a toolkit for finding bounds when predicting behaviours based upon nonexperimental and experimental data.

For the past few years, the author, a renowned economist, has been applying the statistical tools of economics to decision making under uncertainty in the context of patient health status and response to treatment. He shows how statistical imprecision and identification problems affect empirical research in the patient-care sphere.

In recent years, there has been a growing interest in applying neural networks to dynamic systems identification (modelling), prediction and control. Neural networks are computing systems characterised by the ability to learn from examples rather than having to be programmed in a conventional sense. Their use enables the behaviour of complex systems to be modelled and predicted and accurate control to be achieved through training, without a priori information about the systems' structures or parameters. This book describes examples of applications of neural networks In modelling, prediction and control. The topics covered include identification of general linear and non-linear processes, forecasting of river levels, stock market prices and currency exchange rates, and control of a time-delayed plant and a two-joint robot. These applications employ the major types of neural networks and learning algorithms. The neural network types considered in detail are the muhilayer perceptron (MLP), the Elman and Jordan networks and the Group-Method-of-Data-Handling (GMDH) network. In addition, cerebellar-model-articulation-controller (CMAC) networks and neuromorphic fuzzy logic systems are also presented. The main learning algorithm adopted in the applications is the standard backpropagation (BP) algorithm. Widrow-Hoff learning, dynamic BP and evolutionary learning are also described.

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.