Description of the figure

This monograph presents a general framework for comparative distributional analysis. It is written for empirical social scientists and statisticians interested in measurement. Differences among groups or changes in the distribution of a variable over time are a common focus of study in the social sciences. Traditional parametric models restrict such analyses to conditional means and variances, leaving much of the distributional information untapped. The methods presented in this book enable researchers to move beyond means-based comparisons to conduct detailed analyses of distributional difference. The framework is based on the relative distribution, a simple transformation of the data that is also a complete nonparametric summary of the information required for scale-invariant distributional comparison. The relative distribution provides a graphical display that simplifies exploratory data analysis, a statistically valid basis for the development of hypothesis-driven summary measures, and location, shape, and covariate decompositions that identify the sources of distributional changes within and between groups. The book can serve as a supplementary text for a course on distributional methods or as a stand-alone text for an advanced methods course. The presentation alternates chapters on theory and methodological development with chapters providing an in-depth practical application.

Mark S. Handcock is Professor of Statistics and Sociology at the University of Washington.
Martina Morris is the Blumstein-Jordan Professor of Sociology and Statistics at the University of Washington.

Contents: Introduction and Motivation.- The Relative Distribution.- Location, Scale and Shape Decomposition.- Application: White Men's Earnings 1967-1997.- Summary Measures.- Application: Earnings by Race and Sex: 1967-1997.- Adjustment for Covariates.- Application: Comparing Wage Mobility in Two Eras.- Inference for the Relative Distribution.- Inference for Summary Measures.- The Relative Distribution for Discrete Data.- Application: Changes in the Distribution of Hours Worked.- Quantile Regression.- Index.

August 1999. 265 pp. 43 figs. Hardcover $59.95 ISBN 0-387-98778-9

Statistics, Social Science, Economics

For researchers, grad students
Level: Reference

Recommended for Bookstores
Appears in the Springer-Verlag Bookstore Catalogs`

How to get a copy?

Copyright ©1999 Springer-Verlag New York, Inc. All rights reserved.