"…the best book to learn matrix and related ideas…statisticians, econometricians, computer scientists, engineers, and psychometricians will find this extremely useful." (Journal of Statistical Computation and Simulation, March 2006)

Over the past 15 years, the availability of cheap and convenient microcomputers has changed the collection methods and analysis of household survey data in developing countries, making the data available within months, rather than years. Simultaneously, analysts have become more interested in exploring ways in which such data may be used to inform and improve the steps involved in policymaking. This book reviews the analysis of household survey data, including the construction of household surveys, the econometric tools that are the most useful for such analysis, and a range of problems in development policy for which the econometric analysis of household surveys is useful and informative. The author's approach remains close to the data, relying on transparent econometric and graphical techniques to present the data so that policy and academic debates are clearly informed. The author illustrates the analysis through examples of policy issues from several countries, including Cote d'Ivoire, India, Pakistan, Taiwan (China), and Thailand. Two introductory chapters discuss the content and construction of surveys, as well as the econometric methods that can be used with survey data. Survey design and sampling are covered in some detail, as are the effect of survey design on the calculation of statistics and the estimation of parameters. A chapter on econometrics explores issues such as heteroskedasticity, sample selection, and instrumental variables. Four chapters focus on poverty and inequality, demand analysis and intrahousehold allocation, price and tax reform, and savings. Each chapter presents a self-contained development of the topic, introduces the important empirical issues, and provides substantive results. The book also includes the computer code used to calculate the results so that readers can adapt the methods to yield similar results for other data.

PDF version of this book from the author's homepage: http://elsa.berkeley.edu/books/choice2.html

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 behaviour.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.

The last decade has brought dramatic changes in the way that researchers analyze economic and financial time series. This book synthesizes these recent advances and makes them accessible to first-year graduate students. James Hamilton provides the first adequate text-book treatments of important innovations such as vector autoregressions, generalized method of moments, the economic and statistical consequences of unit roots, time-varying variances, and nonlinear time series models. In addition, he presents basic tools for analyzing dynamic systems (including linear representations, autocovariance generating functions, spectral analysis, and the Kalman filter) in a way that integrates economic theory with the practical difficulties of analyzing and interpreting real-world data. "Time Series Analysis" fills an important need for a textbook that integrates economic theory, econometrics, and new results. The book is intended to provide students and researchers with a self-contained survey of time series analysis. It starts from first principles and should be readily accessible to any beginning graduate student, while it is also intended to serve as a reference book for researchers.

This is the first volume in a major two-volume set of advanced texts in econometrics. It is essentially a text in statistics which is adapted to deal with economic phenomena. Christian Gourieroux and Alain Monfort have written a text which synthesises a great deal of material scattered across a variety of books and journals. They present both the basic and the more sophisticated statistical models which are crucial to an understanding of econometric models, and have taken care to employ mathematical tools with which a majority of students with a basic course in econometrics will be familiar. One of the most attractive features of the books is the liberal use throughout of real-world economic examples. They are also distinctive for their emphasis on promoting an intuitive understanding of the models and results at the expense of overly technical discussions.

This two-volume work aims to present as completely as possible the methods of statistical inference with special reference to their economic applications. The reader will find a description not only of the classical concepts and results of mathematical statistics, but also of concepts and methods recently developed for the specific needs of econometrics. The authors have sought to avoid an overly technical presentation and go to some lengths to encourage an intuitive understanding of the results by providing numerous examples throughout. The breadth of approaches and the extensive coverage of the two volumes provide for a thorough and entirely self-contained course in modern econometrics. Volume 1 provides an introduction to general concepts and methods in statistics and econometrics, and goes on to cover estimation and prediction. Volume 2 focuses on testing, confidence regions, model selection, and asymptotic theory.

Time Series: Theory and Methods is a systematic account of linear time series models and their application to the modelling and prediction of data collected sequentially in time. The aim is to provide specific techniques for handling data and at the same time to provide a thorough understanding of the mathematical basis for techniques. Both time and frequency domain methods are discussed, but the book is written in such a way that either approach could be emphasized. The book intended to be a text for graduate students in statistics, mathematics, engineering, and the natural or social sciences. It contains substantial chapters on multivariate series and state-space models (including applications of the Kalman recursions to missing-value problems) and shorter accounts of special topics including long-range dependence, infinite variance processes and non-linear models. Most of the programs used in the book are available on diskettes for the IBM-PC. These diskettes, with the accompanying manual, ITSM: The Interactive Time Series Modelling Package for the PC, also by Brockwell and Davis, can be purchased from Springer-Verlag.

Standard methods for estimating empirical models in economics and many other fields rely on strong assumptions about functional forms and the distributions of unobserved random variables. Often, it is assumed that functions of interest are linear or that unobserved random variables are normally distributed. Such assumptions simplify estimation and statistical inference but are rarely justified by economic theory or other a priori considerations. Inference based on convenient but incorrect assumptions about functional forms and distributions can be highly misleading. Nonparametric and semiparametric statistical methods provide a way to reduce the strength of the assumptions required for estimation and inference, thereby reducing the opportunities for obtaining misleading results. These methods are applicable to a wide variety of estimation problems in empirical economics and other fields, and they are being used in applied research with increasing frequency. The literature on nonparametric and semiparametric estimation is large and highly technical. This book presents the main ideas underlying a variety of nonparametric and semiparametric methods. It is accessible to graduate students and applied researchers who are familiar with econometric and statistical theory at the level taught in graduate-level courses in leading universities. The book emphasizes ideas instead of technical details and provides as intuitive an exposition as possible. Empirical examples illustrate the methods that are presented. This book updates and greatly expands the author's previous book on semiparametric methods in econometrics. Nearly half of the material is new.

In this book Christian Gourieroux and Alain Monfort provide an up-to-date and comprehensive analysis of modern time series econometrics. They have succeeded in synthesising in an organised and integrated way a broad and diverse literature. While the book does not assume a deep knowledge of economics, one of its most attractive features is the close attention it pays to economic models and phenomena throughout. The coverage represents a major reference tool for graduate students, researchers and applied economists. The book is divided into four sections. Section one gives a detailed treatment of classical seasonal adjustment or smoothing methods. Section two provides a thorough coverage of various mathematical tools. Section three is the heart of the book, and is devoted to a range of important topics including causality, exogeneity shocks, multipliers, cointegration and fractionally integrated models. The final section describes the main contribution of filtering and smoothing theory to time series econometric problems.

A Turing Award-winning computer scientist and statistician shows how understanding causality has revolutionized science and will revolutionize artificial intelligence
“Correlation is not causation.” This mantra, chanted by scientists for more than a century, has led to a virtual prohibition on causal talk. Today, that taboo is dead. The causal revolution, instigated by Judea Pearl and his colleagues, has cut through a century of confusion and established causality–the study of cause and effect–on a firm scientific basis. His work explains how we can know easy things, like whether it was rain or a sprinkler that made a sidewalk wet; and how to answer hard questions, like whether a drug cured an illness. Pearl’s work enables us to know not just whether one thing causes another: it lets us explore the world that is and the worlds that could have been. It shows us the essence of human thought and key to artificial intelligence. Anyone who wants to understand either needs The Book of Why.

Most questions in social and biomedical sciences are causal in nature: what would happen to individuals, or to groups, if part of their environment were changed? In this groundbreaking text, two world-renowned experts present statistical methods for studying such questions. This book starts with the notion of potential outcomes, each corresponding to the outcome that would be realized if a subject were exposed to a particular treatment or regime. In this approach, causal effects are comparisons of such potential outcomes. The fundamental problem of causal inference is that we can only observe one of the potential outcomes for a particular subject. The authors discuss how randomized experiments allow us to assess causal effects and then turn to observational studies. They lay out the assumptions needed for causal inference and describe the leading analysis methods, including, matching, propensity-score methods, and instrumental variables. Many detailed applications are included, with special focus on practical aspects for the empirical researcher.

The primary purpose of this book is to prepare students for empirical research in economics. But it also equips those who plan to specialize in econometric theory and those whose empirical interests are in sociology or business. Aimed at first-year graduate students and advanced undergraduates, "A Course in Econometrics" covers the fundamentals - classical regression and simultaneous equations - but also contains clear treatments of symptotic theory and nonlinear regression. The innovative features of the text include: (1) a focus on the conditional expectation function and best linear predictor as interesting characteristics of a population: (2) a thoughtful interpretation of assumptions on the disturbance term in linear regression; (3) a consistent development of estimators as sample analogs of population parameters; (4) a careful discussion of alternative sampling schemes to clarify the distinction between random and idea explanatory variables; (5) a development of asymptotic theory that emphasizes a simple prototypical case; (6) a cautionary treatment of the use and abuse of significance tests; (7) an introduction to simultaneous equation models that focuses on structural parameters as invariant across populations. The text includes instructive exercises and graphs, along with several complete data sets.