The Relative Performance Index: Neutralizing Simpson's Paradox

Ernest C Davenport, Kyle Nickodem, Mark L Davison, Gareth Phillips, Edmund Graham

Research output: Contribution to journalArticle

Abstract

Comparing populations on one or more variables is often of interest. These comparisons are typically made using the mean; however, it is well known that mean comparisons can lead to misinterpretation because of Simpson's paradox. Simpson's paradox occurs when there is a differential distribution of subpopulations across the populations being compared and the means of those subpopulations are different. This article develops the relative performance index (RPI) to ameliorate effects of Simpson's paradox. Data from the National Assessment of Educational Progress (NAEP) are used to illustrate use of the new index. The utility of RPI is compared to the population mean and a prior index, the balanced index. This article shows how RPI can be generalized to a variety of contexts with implications for decision making.

Original languageEnglish (US)
Pages (from-to)1-8
Number of pages8
JournalAmerican Statistician
DOIs
StateAccepted/In press - Jun 20 2018

Fingerprint

Simpson's Paradox
Performance Index
Decision Making
Relative performance
Paradox
Performance index

Keywords

  • Means
  • Mixture distributions
  • Multiple populations
  • Simpson's paradox

Cite this

The Relative Performance Index : Neutralizing Simpson's Paradox. / Davenport, Ernest C; Nickodem, Kyle; Davison, Mark L; Phillips, Gareth; Graham, Edmund.

In: American Statistician, 20.06.2018, p. 1-8.

Research output: Contribution to journalArticle

@article{3522f79686cc4ba09e8f42d5b814c1d4,
title = "The Relative Performance Index: Neutralizing Simpson's Paradox",
abstract = "Comparing populations on one or more variables is often of interest. These comparisons are typically made using the mean; however, it is well known that mean comparisons can lead to misinterpretation because of Simpson's paradox. Simpson's paradox occurs when there is a differential distribution of subpopulations across the populations being compared and the means of those subpopulations are different. This article develops the relative performance index (RPI) to ameliorate effects of Simpson's paradox. Data from the National Assessment of Educational Progress (NAEP) are used to illustrate use of the new index. The utility of RPI is compared to the population mean and a prior index, the balanced index. This article shows how RPI can be generalized to a variety of contexts with implications for decision making.",
keywords = "Means, Mixture distributions, Multiple populations, Simpson's paradox",
author = "Davenport, {Ernest C} and Kyle Nickodem and Davison, {Mark L} and Gareth Phillips and Edmund Graham",
year = "2018",
month = "6",
day = "20",
doi = "10.1080/00031305.2018.1451777",
language = "English (US)",
pages = "1--8",
journal = "American Statistician",
issn = "0003-1305",
publisher = "American Statistical Association",

}

TY - JOUR

T1 - The Relative Performance Index

T2 - Neutralizing Simpson's Paradox

AU - Davenport, Ernest C

AU - Nickodem, Kyle

AU - Davison, Mark L

AU - Phillips, Gareth

AU - Graham, Edmund

PY - 2018/6/20

Y1 - 2018/6/20

N2 - Comparing populations on one or more variables is often of interest. These comparisons are typically made using the mean; however, it is well known that mean comparisons can lead to misinterpretation because of Simpson's paradox. Simpson's paradox occurs when there is a differential distribution of subpopulations across the populations being compared and the means of those subpopulations are different. This article develops the relative performance index (RPI) to ameliorate effects of Simpson's paradox. Data from the National Assessment of Educational Progress (NAEP) are used to illustrate use of the new index. The utility of RPI is compared to the population mean and a prior index, the balanced index. This article shows how RPI can be generalized to a variety of contexts with implications for decision making.

AB - Comparing populations on one or more variables is often of interest. These comparisons are typically made using the mean; however, it is well known that mean comparisons can lead to misinterpretation because of Simpson's paradox. Simpson's paradox occurs when there is a differential distribution of subpopulations across the populations being compared and the means of those subpopulations are different. This article develops the relative performance index (RPI) to ameliorate effects of Simpson's paradox. Data from the National Assessment of Educational Progress (NAEP) are used to illustrate use of the new index. The utility of RPI is compared to the population mean and a prior index, the balanced index. This article shows how RPI can be generalized to a variety of contexts with implications for decision making.

KW - Means

KW - Mixture distributions

KW - Multiple populations

KW - Simpson's paradox

UR - http://www.scopus.com/inward/record.url?scp=85048871383&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048871383&partnerID=8YFLogxK

U2 - 10.1080/00031305.2018.1451777

DO - 10.1080/00031305.2018.1451777

M3 - Article

SP - 1

EP - 8

JO - American Statistician

JF - American Statistician

SN - 0003-1305

ER -