Show simple item record

dc.contributor.authorSpanos, Aen_US
dc.date.accessioned2017-03-13T19:20:44Z
dc.date.available2017-03-13T19:20:44Z
dc.identifier.urihttp://hdl.handle.net/10919/76645
dc.description.abstractThe primary objective of this paper is to revisit Simpson's paradox using a statistical misspecification perspective. It is argued that the reversal of statistical associations is sometimes spurious, stemming from invalid probabilistic assumptions imposed on the data. The concept of statistical misspecification is used to formalize the vague term `spurious results' as `statistically untrustworthy' inference results. This perspective sheds new light on the paradox by distingusing between statistically trustworthy vs. untrustworthy association reversals. It turns out that in both cases there is nothing counterintuitive to explain or account for. This perspective is also used to revisit the causal `resolution' of the paradox in an attempt to delineate the modeling and inference issues raised by the statistical misspecification perspective. The main arguments are illustrated using both actual and hypothetical data from the literature, including Yule's "nonsense-correlations" and the Berkeley admissions study.en_US
dc.relation.urihttp://arxiv.org/abs/1605.02209v2en_US
dc.subjectstat.MEen_US
dc.subjectstat.MEen_US
dc.titleRevisiting Simpson's Paradox: a statistical misspecification perspectiveen_US
dc.typeArticle - Refereed
dc.description.notes24 pages, 12 figuresen_US
dc.identifier.orcidSpanos, A [0000-0002-9229-424X]en_US
pubs.organisational-group/Virginia Tech
pubs.organisational-group/Virginia Tech/All T&R Faculty
pubs.organisational-group/Virginia Tech/Science
pubs.organisational-group/Virginia Tech/Science/COS T&R Faculty
pubs.organisational-group/Virginia Tech/Science/Economics


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record