Extreme-groups designs in studies of dimensional phenomena: Advantages, caveats, and recommendations

Joscelyn E. Fisher, Anika Guha, Wendy Heller, Gregory A. Miller

Research output: Contribution to journalArticle

Abstract

Extreme-groups designs (EGDs) are common in psychopathology research, often using diagnostic category as an independent variable. Continuous-variable analysis strategies drawing from a general linear model framework can be applied to such designs. The growing emphasis on dimensional examinations of psychological constructs, encouraged by the National Institute of Mental Health Research Domain Criteria framework, encourages continuous-variable analytic strategies. However, the interpretative implications of applying these strategies to various types of populations and sample score distributions, including those used in EGDs, are not always recognized. Appropriateness and utility of EGDs depend in part on whether the goal is to determine whether a relationship exists between 2 variables or to determine its strength. Whereas the literature investigating EGDs has emphasized symmetrical thresholds for defining extreme groups (e.g., bottom 10% vs. top 10%), psychopathologists often employ asymmetric thresholds (e.g., above a diagnostic threshold vs. a broader range of scores in a healthy comparison group). The present article selectively reviews literature on EGDs and extends it with simulations of symmetric and asymmetric selection criteria. Results indicate that including a wide range of scores in EGDs substantially mitigates problems (e.g., inflation of effect size) that arise when using statistical methods classically employed for continuous variables.

Original languageEnglish (US)
Pages (from-to)14-20
Number of pages7
JournalJournal of abnormal psychology
Volume129
Issue number1
DOIs
StatePublished - Jan 2020

Fingerprint

National Institute of Mental Health (U.S.)
Economic Inflation
Psychopathology
Research
Patient Selection
Linear Models
Psychology
Population

Keywords

  • Effect size inflation
  • Experimental design
  • Extreme-groups design

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry

Cite this

Extreme-groups designs in studies of dimensional phenomena : Advantages, caveats, and recommendations. / Fisher, Joscelyn E.; Guha, Anika; Heller, Wendy; Miller, Gregory A.

In: Journal of abnormal psychology, Vol. 129, No. 1, 01.2020, p. 14-20.

Research output: Contribution to journalArticle

Fisher, Joscelyn E. ; Guha, Anika ; Heller, Wendy ; Miller, Gregory A. / Extreme-groups designs in studies of dimensional phenomena : Advantages, caveats, and recommendations. In: Journal of abnormal psychology. 2020 ; Vol. 129, No. 1. pp. 14-20.
@article{05fd0919135e4687a84d474005cd116a,
title = "Extreme-groups designs in studies of dimensional phenomena: Advantages, caveats, and recommendations",
abstract = "Extreme-groups designs (EGDs) are common in psychopathology research, often using diagnostic category as an independent variable. Continuous-variable analysis strategies drawing from a general linear model framework can be applied to such designs. The growing emphasis on dimensional examinations of psychological constructs, encouraged by the National Institute of Mental Health Research Domain Criteria framework, encourages continuous-variable analytic strategies. However, the interpretative implications of applying these strategies to various types of populations and sample score distributions, including those used in EGDs, are not always recognized. Appropriateness and utility of EGDs depend in part on whether the goal is to determine whether a relationship exists between 2 variables or to determine its strength. Whereas the literature investigating EGDs has emphasized symmetrical thresholds for defining extreme groups (e.g., bottom 10{\%} vs. top 10{\%}), psychopathologists often employ asymmetric thresholds (e.g., above a diagnostic threshold vs. a broader range of scores in a healthy comparison group). The present article selectively reviews literature on EGDs and extends it with simulations of symmetric and asymmetric selection criteria. Results indicate that including a wide range of scores in EGDs substantially mitigates problems (e.g., inflation of effect size) that arise when using statistical methods classically employed for continuous variables.",
keywords = "Effect size inflation, Experimental design, Extreme-groups design",
author = "Fisher, {Joscelyn E.} and Anika Guha and Wendy Heller and Miller, {Gregory A.}",
year = "2020",
month = "1",
doi = "10.1037/abn0000480",
language = "English (US)",
volume = "129",
pages = "14--20",
journal = "Journal of Abnormal Psychology",
issn = "0021-843X",
publisher = "American Psychological Association Inc.",
number = "1",

}

TY - JOUR

T1 - Extreme-groups designs in studies of dimensional phenomena

T2 - Advantages, caveats, and recommendations

AU - Fisher, Joscelyn E.

AU - Guha, Anika

AU - Heller, Wendy

AU - Miller, Gregory A.

PY - 2020/1

Y1 - 2020/1

N2 - Extreme-groups designs (EGDs) are common in psychopathology research, often using diagnostic category as an independent variable. Continuous-variable analysis strategies drawing from a general linear model framework can be applied to such designs. The growing emphasis on dimensional examinations of psychological constructs, encouraged by the National Institute of Mental Health Research Domain Criteria framework, encourages continuous-variable analytic strategies. However, the interpretative implications of applying these strategies to various types of populations and sample score distributions, including those used in EGDs, are not always recognized. Appropriateness and utility of EGDs depend in part on whether the goal is to determine whether a relationship exists between 2 variables or to determine its strength. Whereas the literature investigating EGDs has emphasized symmetrical thresholds for defining extreme groups (e.g., bottom 10% vs. top 10%), psychopathologists often employ asymmetric thresholds (e.g., above a diagnostic threshold vs. a broader range of scores in a healthy comparison group). The present article selectively reviews literature on EGDs and extends it with simulations of symmetric and asymmetric selection criteria. Results indicate that including a wide range of scores in EGDs substantially mitigates problems (e.g., inflation of effect size) that arise when using statistical methods classically employed for continuous variables.

AB - Extreme-groups designs (EGDs) are common in psychopathology research, often using diagnostic category as an independent variable. Continuous-variable analysis strategies drawing from a general linear model framework can be applied to such designs. The growing emphasis on dimensional examinations of psychological constructs, encouraged by the National Institute of Mental Health Research Domain Criteria framework, encourages continuous-variable analytic strategies. However, the interpretative implications of applying these strategies to various types of populations and sample score distributions, including those used in EGDs, are not always recognized. Appropriateness and utility of EGDs depend in part on whether the goal is to determine whether a relationship exists between 2 variables or to determine its strength. Whereas the literature investigating EGDs has emphasized symmetrical thresholds for defining extreme groups (e.g., bottom 10% vs. top 10%), psychopathologists often employ asymmetric thresholds (e.g., above a diagnostic threshold vs. a broader range of scores in a healthy comparison group). The present article selectively reviews literature on EGDs and extends it with simulations of symmetric and asymmetric selection criteria. Results indicate that including a wide range of scores in EGDs substantially mitigates problems (e.g., inflation of effect size) that arise when using statistical methods classically employed for continuous variables.

KW - Effect size inflation

KW - Experimental design

KW - Extreme-groups design

UR - http://www.scopus.com/inward/record.url?scp=85074659090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074659090&partnerID=8YFLogxK

U2 - 10.1037/abn0000480

DO - 10.1037/abn0000480

M3 - Article

C2 - 31657600

AN - SCOPUS:85074659090

VL - 129

SP - 14

EP - 20

JO - Journal of Abnormal Psychology

JF - Journal of Abnormal Psychology

SN - 0021-843X

IS - 1

ER -