The Intervention Selection Bias: An Underrecognized Confound in Intervention Research

Robert E. Larzelere, Brett R Kuhn, Byron Johnson

Research output: Contribution to journalReview article

80 Citations (Scopus)

Abstract

Selection bias can be the most important threat to internal validity in intervention research, but is often insufficiently recognized and controlled. The bias is illustrated in research on parental interventions (punishment, homework assistance); medical interventions (hospitalization); and psychological interventions for suicide risk, sex offending, and juvenile delinquency. The intervention selection bias is most adequately controlled in randomized studies or strong quasi-experimental designs, although recent statistical innovations can enhance weaker designs. The most important points are to increase awareness of the intervention selection bias and to systematically evaluate plausible alternative explanations of data before making causal conclusions.

Original languageEnglish (US)
Pages (from-to)289-303
Number of pages15
JournalPsychological Bulletin
Volume130
Issue number2
DOIs
StatePublished - Mar 1 2004

Fingerprint

Selection Bias
Juvenile Delinquency
Research
Punishment
Suicide
Hospitalization
Research Design
Psychology

ASJC Scopus subject areas

  • Psychology(all)

Cite this

The Intervention Selection Bias : An Underrecognized Confound in Intervention Research. / Larzelere, Robert E.; Kuhn, Brett R; Johnson, Byron.

In: Psychological Bulletin, Vol. 130, No. 2, 01.03.2004, p. 289-303.

Research output: Contribution to journalReview article

Larzelere, Robert E. ; Kuhn, Brett R ; Johnson, Byron. / The Intervention Selection Bias : An Underrecognized Confound in Intervention Research. In: Psychological Bulletin. 2004 ; Vol. 130, No. 2. pp. 289-303.
@article{8ea27d285b17426181c2a21502437ea6,
title = "The Intervention Selection Bias: An Underrecognized Confound in Intervention Research",
abstract = "Selection bias can be the most important threat to internal validity in intervention research, but is often insufficiently recognized and controlled. The bias is illustrated in research on parental interventions (punishment, homework assistance); medical interventions (hospitalization); and psychological interventions for suicide risk, sex offending, and juvenile delinquency. The intervention selection bias is most adequately controlled in randomized studies or strong quasi-experimental designs, although recent statistical innovations can enhance weaker designs. The most important points are to increase awareness of the intervention selection bias and to systematically evaluate plausible alternative explanations of data before making causal conclusions.",
author = "Larzelere, {Robert E.} and Kuhn, {Brett R} and Byron Johnson",
year = "2004",
month = "3",
day = "1",
doi = "10.1037/0033-2909.130.2.289",
language = "English (US)",
volume = "130",
pages = "289--303",
journal = "Psychological Bulletin",
issn = "0033-2909",
publisher = "American Psychological Association Inc.",
number = "2",

}

TY - JOUR

T1 - The Intervention Selection Bias

T2 - An Underrecognized Confound in Intervention Research

AU - Larzelere, Robert E.

AU - Kuhn, Brett R

AU - Johnson, Byron

PY - 2004/3/1

Y1 - 2004/3/1

N2 - Selection bias can be the most important threat to internal validity in intervention research, but is often insufficiently recognized and controlled. The bias is illustrated in research on parental interventions (punishment, homework assistance); medical interventions (hospitalization); and psychological interventions for suicide risk, sex offending, and juvenile delinquency. The intervention selection bias is most adequately controlled in randomized studies or strong quasi-experimental designs, although recent statistical innovations can enhance weaker designs. The most important points are to increase awareness of the intervention selection bias and to systematically evaluate plausible alternative explanations of data before making causal conclusions.

AB - Selection bias can be the most important threat to internal validity in intervention research, but is often insufficiently recognized and controlled. The bias is illustrated in research on parental interventions (punishment, homework assistance); medical interventions (hospitalization); and psychological interventions for suicide risk, sex offending, and juvenile delinquency. The intervention selection bias is most adequately controlled in randomized studies or strong quasi-experimental designs, although recent statistical innovations can enhance weaker designs. The most important points are to increase awareness of the intervention selection bias and to systematically evaluate plausible alternative explanations of data before making causal conclusions.

UR - http://www.scopus.com/inward/record.url?scp=1542267892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1542267892&partnerID=8YFLogxK

U2 - 10.1037/0033-2909.130.2.289

DO - 10.1037/0033-2909.130.2.289

M3 - Review article

C2 - 14979773

AN - SCOPUS:1542267892

VL - 130

SP - 289

EP - 303

JO - Psychological Bulletin

JF - Psychological Bulletin

SN - 0033-2909

IS - 2

ER -