Last modified: 2018-05-18
Abstract
The dissimilarity index is widely used to evaluate residential segregation, although there is a widespread awareness that this index is inherently subject to an upward bias and, under certain conditions, can be highly misleading. Common strategies used in literature to deal with the index bias rely on the use of informal rules of thumb, which at least have the side effect of restricting the scope of segregation studies.
Bias correction methods have been proposed, but they require the computation of the sampling distribution of the index through computation-intensive techniques and the lack of user-friendly computer programs has affected their adoption. Hence, we introduce an R package that allows for the computation of bias corrections based on bootstrap, iterated bootstrap, grouped jackknife, and on a technique proposed by the authors. Confidence intervals and tests for absence of segregation are implemented.
References
1. Allen, R., S. Burgess, and F. Windmeijer: More Reliable Inference for Segregation Indices. Technical Report 216, The Centre for Market and Public Organisation, University of Bristol, Bristol, UK (2009)
2. Altavilla A.M., Mazza A., Punzo A.: Sull’impiego di un indice di dissimilarità nello studio della disposizione di popolazioni straniere su un territorio urbano. Rivista Italiana di Economia, Demografia e Statistica, vol. LXIV, p. 7-14 (2010)
3. Duncan, O. D. and B. Duncan: A Methodological Analysis of Segregation Indexes. American Sociological Review 20:210-217 (1955)
4. Massey D. S., Denton, N. A.: The dimensions of residential segregation. Social Forces, 67(2), 281–315 (1988)
5. Mazza, A., Punzo, A.: On the upward bias of the dissimilarity index and its corrections. Sociological Methods & Research 44(1): 80–107 (2015).
6. R Core Team. R: A Language and Environment for Statistical Computing. R Foundation for Statistical Computing, Vienna, Austria. URL http://www.R-project.org/ (2017).