|
gptkbp:instanceOf
|
gptkb:statistical_phenomenon
|
|
gptkbp:alsoKnownAs
|
gptkb:Yule–Simpson_effect
|
|
gptkbp:category
|
paradox in statistics
statistical fallacy
|
|
gptkbp:describedBy
|
gptkb:Simpson,_E._H._(1951)_'The_Interpretation_of_Interaction_in_Contingency_Tables'
|
|
gptkbp:example
|
gptkb:Berkeley_gender_bias_case
Kidney stone treatment study
|
|
gptkbp:field
|
gptkb:probability_theory
statistics
|
|
gptkbp:firstDescribed
|
1951
|
|
gptkbp:implies
|
importance of considering subgroup analysis
misleading conclusions from aggregated data
potential for reversal of association direction
|
|
gptkbp:namedAfter
|
gptkb:Edward_H._Simpson
|
|
gptkbp:occurredIn
|
a trend appears in several different groups of data but disappears or reverses when these groups are combined
|
|
gptkbp:relatedTo
|
causal inference
aggregation
confounding variable
|
|
gptkbp:studiedIn
|
gptkb:medicine
data science
economics
epidemiology
social sciences
|
|
gptkbp:bfsParent
|
gptkb:Yule–Simpson_effect
|
|
gptkbp:bfsLayer
|
5
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Simpson's paradox
|