Heteroskedasticity in Regression

Detection and Correction
1. Auflage 2013
ISBN: 978-1-4522-3495-3
Verlag: Sage Publications, Inc

Buch, Englisch, Band 172, 112 Seiten, Paperback, Format (B × H): 140 mm x 216 mm, Gewicht: 155 g

Reihe: Quantitative Applications in the Social Sciences

This volume covers the commonly ignored topic of heteroskedasticity (unequal error variances) in regression analyses and provides a practical guide for how to proceed in terms of testing and correction. Emphasizing how to apply diagnostic tests and corrections for heteroskedasticity in actual data analyses, the book offers three approaches for dealing with heteroskedasticity:

- variance-stabilizing transformations of the dependent variable;
- calculating robust standard errors, or heteroskedasticity-consistent standard errors; and
- generalized least squares estimation coefficients and standard errors.

The detection and correction of heteroskedasticity is illustrated with three examples that vary in terms of sample size and the types of units analyzed (individuals, households, U.S. states). Intended as a supplementary text for graduate-level courses and a primer for quantitative researchers, the book fills the gap between the limited coverage of heteroskedasticity provided in applied regression textbooks and the more theoretical statistical treatment in advanced econometrics textbooks.

Autoren/Hrsg.

Kaufman, Robert L.

Fachgebiete

• Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Forschungsmethodik, Wissenschaftliche Ausstattung

Inhaltsverzeichnis

Series Editor's Introduction
About the Authors
Acknowledgements
1. What Is Heteroskedasticity and Why Should We Care?
2. Detecting and Diagnosing Heteroskedasticity
3. Variance-Stabilizing Transformations To Correct For Heteroskedasticity
4. Heteroskedasticity Consistent (Robust) Standard Errors
5. (Estimated) Generalized Least Squares Regression Model For Heteroskedasticity
6. Choosing Among Correction Options
References
Appendix: Miscellaneous Derivations and Tables

Über Autor(innen)

Kaufman, Robert L.
Robert Kaufman (PhD University of Wisconsin, 1981) is professor of sociology and the Chair of the Department of Sociology at Temple University. His substantive research focuses on economic structure and labor market inequality, especially with respect to race, ethnicity, and gender. He has also explored other realms of race-ethnic inequality, including research on wealth, home equity, residential segregation, traffic stops and treatment by police, and media portrayals of crime. More abstract statistical issues motivate some of his current work on evaluating different methods for correcting for heteroskedasticity using Monte Carlo simulations. Dr. Kaufman has published papers on quantitative methods in American Sociological Review, American Journal of Sociology, Sociological Methodology, Sociological Methods and Research, and Social Science Quarterly. He served on the editorial board of Sociological Methods and Research for 15 years and has taught graduate-level statistics courses nearly every year for the past 30 years.

Robert Kaufman (Ph.D. University of Wisconsin, 1981) is Professor of Sociology and the Chair of the Department of Sociology at Temple University. His research primarily focuses on economic structure and labor market inequality, especially with respect to race, ethnicity, and gender. For example, he studies how job segregation and devaluation processes create and reproduce race and gender inequalities in job rewards. Throughout his career, he has also explored other realms of race-ethnic inequality, including research on wealth, home equity, residential segregation, traffic stops and treatment by police, and most recently on media portrayals of crime. In terms of his interests in applied statistics and quantitative methodology, his research has usually been explicitly tied to particular substantive questions such as how to estimate "tolerable" segregation, the use of cluster analysis to define economic segments, or the use of multiplicity sampling of workers to create a representative sample of work organizations. However, more abstract statistical issues motivate some of his current work on evaluating different methods for correcting for heteroskedasticity using Monte Carlo simulations. Dr. Kaufman has published papers on quantitative methods in a variety of journals, including American Sociological Review, American Journal of Sociology, Sociological Methodology, Sociological Methods and Research, and Social Science Quarterly. He served on the editorial board of Sociological Methods and Research for 15 years. He has taught graduate-level statistics course nearly every year for the past 30 years, either a basic, applied regression course or more advanced courses on topics such as generalized least squares, log-linear analysis, logistic regression and other models for limited dependent variables.