Developing Econometrics, by Hengqing Tong, T. Krishna Kumar, and Yangxin Huang, 2011, West Sussex, UK: John Wiley & Sons, Ltd., 486 pages. ISBN: 978‐0470681770.

• Date: 01 March 2014
• DOI: http://doi.org/10.1111/jori.12029
• Published date: 01 March 2014

BOOK REVIEW

Developing Econometrics, by Hengqing Tong, T. Krishna Kumar, and Yangxin Huang,

2011, West Sussex, UK: John Wiley & Sons, Ltd., 486 pages. ISBN: 978-0470681770.

Reviewer: Lisa A. Gardner, Drake University; lisa.gardner@drake.edu

Hengqing Tong, T. Krishna Kumar, and Yangxin Huang’s graduate-level text,

Developing Econometrics, like most graduate-level applied econometrics texts,

emphasizes statistical theories and applications in economics and finance. A

particular strength of the book is its international flavor; nearly all of the examples

provided in the text and supplementary material involve countries other than the

United States. The authors include a number of examples from China and India, as

well as from Brazil, France, Japan, Russia, and the United Kingdom. Of course

contextualizing the results from certain problems may prove challenging to those

not having an appropriate international economics and finance background. But

interpretation is not what the book emphasizes; instead, the authors emphasize

calculations using linear algebra, probability and statistics (theory), and a customized

statistical software package, DASC (practice).

The text includes 10 chapters, most of which are devoted at least in part to discussions

about regression or time series models, the bread-and-butter tools for most

economists. The authors provide the usual overview of the text in the first chapter,

including a short introduction to cross-sectional, panel (multiple consecutive time

periods of cross-sectional data), and time series data sets typically considered in the

text. Chapters 2–5 emphasize analyzing cross-sectional data using regression models.

In Chapter 2, the authors introduce simple and multiple regression, data trans-

formations, multicollinearity and ridge regression, and independent variable

reduction using principal components analysis. The focus of Chapter 3 falls first

on error terms, specifically detecting and addressing heteroskedasticity, autocorrela-

tion, and second on working with panel data using random effect regression and

ways of solving variance component models. Chapter 4 concerns regression

modeling with categorical independent variables, discrete or categorical dependent

variables, and nonlinear functions to estimate growth curves and total factor

productivity, for example. Chapter 5 addresses stochastic frontier regression, and

nonparametric and semiparametric regression.

The models examined in Chapters 2–5 mainly employ a single regression equation,

with one dependent variable and at least one independent variable, and primarily

© The Journal of Risk and Insurance, 2014, Vol. 81, No. 1, 237–239

DOI: 10.1111/jori.12029

237