Product Description

A unified treatment of the most useful models for categorical and limited dependent variables (CLDVs) is provided in this book. Throughout, the links among the models are made explicit, and common methods of derivation, interpretation and testing are applied. In addition, the author explains how models relate to linear regression models whenever possible.

After a review of the linear regression model and an introduction to maximum likelihood estimation, the book then: covers the logit and probit models for binary outcomes; reviews standard statistical tests associated with maximum likelihood estimation; and considers a variety of measures for assessing the fit of a model. J Scott Long also: extends the binary logit and probit models to ordered outcomes; presents the multinomial and conditioned logit models for nominal outcomes; considers models with censored and truncated dependent variables with a focus on the tobit model; describes models for sample selection bias; presents models for count outcomes by beginning with the Poisson regression model; and compares the models from earlier chapters, discussing the links between these models and others not discussed in the book.

Product Details

• Amazon Sales Rank: #507833 in Books
• Published on: 1997-02-21
• Original language: English
• Number of items: 1
• Binding: Hardcover
• 328 pages

Review

"Regression Models for Categorical and Limited Dependent Variables excels at explaining applications of nonlinear regression models. . . The  book provides much practical guidance for the estimation, identification, and validation of models for CLDVs. Each chapter is interspersed with exercises and helpful questions. In summary, the author exceeds his goal to provide ‘a firm foundation’ for further reading from the vast and growing literature on limited and categorical dependent variables."

Customer Reviews

not-so-technical applied statistics book
This is a not-so-technical book on intermediate statistics, with a focus on social science application: sociology, economics, demography, politics etc.

By 'non-technical' I mean compared to all other intermediate level textbooks on econometrics (and statistics).
It is not a book for complete beginners, it assumes you have done a first-year course in statistics or econometrics on the level of Undergraduate Econometrics (Hill), Basic Econometrics (Gujarati) etc. It also assumes you know first-year calculus and matrix algebra, ideally on the level of Schaum's Outline of Introduction to Mathematical Economics (Schaum's Outline) (Dowling)or Fundamental Methods of Mathematical Economics (Chiang), but even with just basic math on the level of Essential Mathematics for Economics and Business (Bradley) or Schaum's Outline of Mathematical Methods for Business and Economics (Schaum's Outline Series) you should be fine.

In the book Professor J.S.Long explains the formulae in words as well as with examples, which are taken from the social sciences: sociology, demography, economics, politics etc. There are more words than formulae, and very, very few mathematical proofs. This book is focused on practicality and interpretation, on helping the empirical researcher develop more precise or more applied statistical techniques.

What is unique to me is how Long discusses the methods in a social science context, most applied books I've seen only give a shallow discussion on application as they tend to be written by statisticians whereas Professor Long is a sociologist: he looks at things from your perspective (if you are a social science student/researcher). The topics the book covers are selected because of their frequent use in social science research.

The only thing I think is missing from this book are more exercises; there are a few exercises in the text of each chapter where you are asked to answer a question he poses, but they are not extensive in any way and are mainly there to see if you follow the concept. I would have liked to see a descent number of exercises.