A Cautionary Note on Estimating the Standard Error of the Gini Index of Inequality: Comment
| Author | Tomson Ogwang |
| Published date | 01 June 2006 |
| Date | 01 June 2006 |
| DOI | http://doi.org/10.1111/j.1468-0084.2006.00168.x |
PRACTITIONERS’ CORNER
A Cautionary Note on Estimating the Standard
Error of the Gini Index of Inequality:
Comment
Tomson Ogwang
Department of Economics, Brock University, St Catharines, ON, Canada
(e-mail: togwang@brocku.ca)
Comment
Modarres and Gastwirth (Oxford Bulletin of Economics and Statistics, 2006,
Vol. 68, pp. 385–390) have made an important contribution to the debate on
the appropriate standard error of the Gini index. At the centre of this debate is
the issue of whether practitioners should be reporting computationally simpler
ordinary least squares (OLS)/weighted least squares (WLS) Gini standard
errors (e.g. Giles, 2004), or computationally more complex standard errors
such as the bootstrap or jackknife, that could, perhaps, be modified to take
sampling design into account (e.g. Sandstrom, Wretman and Walden, 1985,
1988; Ogwang, 2000). Modarres and Gastwirth have made a case against the
regression (or stochastic) approach to estimating the standard error of the Gini
index.
As noted by Ogwang (2000, 2004), the regression approach requires
specific assumptions about the error term in the underlying regression model,
which could be exploited in the derivation of Gini standard errors. To this end,
Giles (2004) exploited the heteroscedasticity assumption to derive Gini
standard errors, which can be conveniently obtained as a by-product of WLS
estimation of the parameters of the underlying regression model. Modarres
and Gastwirth have considered how the dependence of the error term, arising
from the ranking of income, the dependent variable in the underlying
JEL Classification numbers: C81, D31.
OXFORD BULLETIN OF ECONOMICS AND STATISTICS, 68, 3 (2006) 0305-9049
391
ÓBlackwell Publishing Ltd, 2006. Published by Blackwell Publishing Ltd, 9600 Garsington Road, Oxford OX4 2DQ, UK
and 350 Main Street, Malden, MA 02148, USA.
To continue reading
Request your trial