Answers are grounded in this paper and cite their sources.
In a recent article in this journal, Latimer and Foss (2005) suggest that Aboriginal youth in five Canadian cities who were sentenced to custody under the Young Offenders Act received longer sentences than did non-Aboriginal youth. This finding is shown to be an artefact of jurisdictional variation. When the cities are looked at individually, or when cities are controlled for in other ways, the effect disappears. This might be seen as an illustration of “Simpson's Paradox,” whereby an association between two variables can be in one direction when pooled across two or more sub-populations but, when looked at individually (within each sub-population), is non-existent or points in the opposite direction.
No takes yet. Share an insight, caveat, or question.
Doob et al. (2007) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: