You are not currently logged in.
Access JSTOR through your library or other institution:
If You Use a Screen ReaderThis content is available through Read Online (Free) program, which relies on page scans. Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Estimation with Cross-National Data: Robust and Nonparametric Methods
Thomas Dietz, R. Scott Frey and Linda Kalof
American Sociological Review
Vol. 52, No. 3 (Jun., 1987), pp. 380-390
Published by: American Sociological Association
Stable URL: http://www.jstor.org/stable/2095357
Page Count: 11
You can always find the topics here!Topics: Population estimates, Standard error, Outliers, Least squares, Statistical estimation, Estimators, Estimation methods, Income inequality, Political sociology, Population distributions
Were these topics helpful?See something inaccurate? Let us know!
Select the topics that are inaccurate.
Since scans are not currently available to screen readers, please contact JSTOR User Support for access. We'll provide a PDF copy for your screen reader.
Preview not available
Researchers often use ordinary least squares regression (OLS) to analyze cross-national and other macrosocial indicator data. Although OLS is a flexible tool, its value depends on a number of assumptions that may be violated when applied to such data. One of the assumptions, the normality of the distribution of population residuals, is essential to efficient and unbiased estimation of regression coefficients and associated standard errors. Robust and bootstrapped regression estimation methods are not sensitive to the normality assumption. Use of these methods in a reestimation of three models from the cross-national literature indicates that OLS may perform poorly when used with cross-national data, and suggests that researchers should be cautious in their use of OLS with such data.
American Sociological Review © 1987 American Sociological Association