Occupational segregation in the multidimensional case: Decomposition and tests of significance

https://doi.org/10.1016/0304-4076(94)90082-5Get rights and content

Abstract

A new multidimensional version of the G-segregation index is developed and applied to the study of occupational segregation. U.S. Current Population Survey data are used to measure the difference in occupational segregation between races as well as the change between time periods. Decomposition of the difference (change) into ‘occupation mix’ and ‘gender composition’ components indicates the contribution of each factor. Because these inequality measures are computed from sample data, distributional information required to test hypotheses is lacking. Two computer-intensive methods for estimating the distributional properties are demonstrated. The approximate randomization and bootstrap methodologies are used to test for statistically significant differences in segregation between races and for changes over time. In addition, the components of the decomposition are examined for statistical significance.

References (20)

  • R.J. Butler

    New indices of segregation

    Economics Letters

    (1987)
  • R.M. Hutchens

    Segregation curves, Lorenz curves and inequality in the distribution of people across occupations

    Mathematical Social Sciences

    (1991)
  • J. Silber

    On the measurement of employment segregation

    Economics Letters

    (1989)
  • Philip M. Dixon et al.

    Bootstrapping the Gini coefficient of inequality

    Ecology

    (1987)
  • O.D. Duncan et al.

    A methodological analysis of segregation indices

    American Sociological Review

    (1955)
  • Eugene S. Edgington

    Approximate randomization tests

    Journal of Psychology

    (1969)
  • Bradley Efron

    Bootstrap methods: Another look at the jackknife

    Annals of Statistics

    (1979)
  • Bradley Efron

    The jackknife, the bootstrap and other resampling plans

    (1982)
  • Bradley Efron et al.

    A leisurely look at the bootstrap, the jackknife, and crossvalidation

    American Statistician

    (1983)
  • R. Fisher

    The fiducial argument in statistical inference

    Annals of Eugenics

    (1935)
There are more references available in the full text version of this article.

Cited by (43)

  • Impact of spatial effects on income segregation indices

    2011, Computers, Environment and Urban Systems
    Citation Excerpt :

    Taeuber and Taeuber (1965) conducts a number of small simulations of Augusta, Georgia, in order to determine if Augusta’s observed segregation level is different from a level that could have occurred from a random allocation of black and white households, and if the difference between Augusta’s and Atlanta’s segregation levels could have occurred from chance variation. In taking the random distribution idea even further, Cortese, Falk, and Cohen (1976) and Winship (1977) use Monte Carlo methods to compute expected values for D for various proportions of the minority population in a city (see Boisso, Hayes, Hirschberg, & Silber, 1994; Noreen, 1989; Carrington & Troske, 1997 for other imlimentations of permutation based approaches). In more recent work, Zhang (2003) implements permutations of empirical data within various US cities to separate out patterns of racial and income segregation, using D as the test statistic.

  • Local versus overall segregation measures

    2010, Mathematical Social Sciences
    Citation Excerpt :

    The study of overall segregation when individuals are classified according to more than two categories has received increasing attention among scholars in recent years. In this vein, Silber (1992) and Boisso et al. (1994) extend the binary segregation indexes proposed by Karmel and MacLachlan (1988) and Silber (1989), respectively. In addition, Reardon and Firebaugh (2002) suggest new overall measures and evaluate them according to a set of axioms, some of them previously established by James and Taeuber (1985).

View all citing articles on Scopus
View full text