Monotone regrouping, regression, and Simpson's Paradox

Yosef Rinott; Michael Tam

doi:10.1198/0003130031397

Monotone regrouping, regression, and Simpson's Paradox

Yosef Rinott^*, Michael Tam

^*Corresponding author for this work

Department of Statistics

Research output: Contribution to journal › Review article › peer-review

9 Scopus citations

Abstract

This article shows in a general setup that if data Y are grouped by a covariate X in a certain way, then under a condition of monotone regression of Y on X, a Simpson's type paradox is natural rather than surprising. This model was motivated by an observation on recent SAT data which are presented.

Original language	English
Pages (from-to)	139-141
Number of pages	3
Journal	American Statistician
Volume	57
Issue number	2
DOIs	https://doi.org/10.1198/0003130031397
State	Published - May 2003

Keywords

Data grouping
Monotone regression func-tion
SAT data

Access to Document

10.1198/0003130031397

Cite this

@article{6bc1ad73f7ab40b1878719ad79f0a4f3,

title = "Monotone regrouping, regression, and Simpson's Paradox",

abstract = "This article shows in a general setup that if data Y are grouped by a covariate X in a certain way, then under a condition of monotone regression of Y on X, a Simpson's type paradox is natural rather than surprising. This model was motivated by an observation on recent SAT data which are presented.",

keywords = "Data grouping, Monotone regression func-tion, SAT data",

author = "Yosef Rinott and Michael Tam",

year = "2003",

month = may,

doi = "10.1198/0003130031397",

language = "אנגלית",

volume = "57",

pages = "139--141",

journal = "American Statistician",

issn = "0003-1305",

publisher = "Taylor and Francis Ltd.",

number = "2",

}

TY - JOUR

T1 - Monotone regrouping, regression, and Simpson's Paradox

AU - Rinott, Yosef

AU - Tam, Michael

PY - 2003/5

Y1 - 2003/5

N2 - This article shows in a general setup that if data Y are grouped by a covariate X in a certain way, then under a condition of monotone regression of Y on X, a Simpson's type paradox is natural rather than surprising. This model was motivated by an observation on recent SAT data which are presented.

AB - This article shows in a general setup that if data Y are grouped by a covariate X in a certain way, then under a condition of monotone regression of Y on X, a Simpson's type paradox is natural rather than surprising. This model was motivated by an observation on recent SAT data which are presented.

KW - Data grouping

KW - Monotone regression func-tion

KW - SAT data

UR - https://www.scopus.com/pages/publications/0037936653

U2 - 10.1198/0003130031397

DO - 10.1198/0003130031397

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.systematicreview???

AN - SCOPUS:0037936653

SN - 0003-1305

VL - 57

SP - 139

EP - 141

JO - American Statistician

JF - American Statistician

IS - 2

ER -

Monotone regrouping, regression, and Simpson's Paradox

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this