Search
   >> Home >> Bookstore >> Social science >> Guide pratique d’introduction à la régression en sciences sociales

Click to enlarge
See the back cover

Guide pratique d’introduction à la régression en sciences sociales

$29.00 each

Authors:
François Pétry and François Gélineau
Publisher: Universite Laval Press
Copyright: 2009
ISBN-13: 978-2-7637-8628-5
Pages: 219; paperback
Price: $29.00
Supplements:Companion website

Comment from the Stata technical group

Guide pratique d’introduction à la régression en sciences sociales, by François Pétry and François Gélineau, offers a brief introduction to exploratory data analysis and applies examples to illustrate the empirical elements associated with linear and logistic regressions.

Chapters 1 and 2 review some of the aspects involved in describing data and preparing them for regression analysis. A number of graphs implemented in Stata are used to examine the behavior of the principal variables associated with the empirical examples.

In chapters 3 and 4, the authors work with data on infant mortality to illustrate the use of simple and multivariate linear regression models. In addition to presenting a series of regression outputs produced in Stata, Pétry and Gélineau describe diagnostic tools that are normally used in standard linear regression.

Chapter 5 provides a short description of the basic elements involved in time-series regression analysis. It discusses the detection of autocorrelation, along with the Prais–Winsten approach to fitting models with autocorrelated errors of order 1. The second part of the chapter describes a case in which government expenses are a function of gross domestic product (GDP). Through the case study, the authors introduce the basic aspects associated with the treatment of nonstationary series in regression analysis. Stata is used to produce most of the graphs and regression outputs contained in this chapter and those that follow.

Chapters 6 and 7 show a case that regards people’s participation in general elections. In chapter 6, the authors fit a logistic model for a binary dependent variable that indicates whether the person voted. The application is extended in chapter 7 by fitting a multinomial model for a categorical dependent variable that is constructed on the basis of participation in the current and previous elections.

The empirical examples and the inclusion of graphs, regression outputs, and summary tables provide smooth reading for the introduction of the technical concepts contained in the text.

Table of contents

View table of contents >>

The Stata Blog: Not Elsewhere Classified Find us on Facebook Follow us on Twitter LinkedIn Google+ Watch us on YouTube