Evaluating Construct Equivalence of Youth Depression Measures Across Multiple Measures and Multiple Studies

George W. Howe, Getachew A. Dagne, C. Hendricks Brown, Ahnalee M. Brincks, William Beardslee, Tatiana Perrino, Hilda Pantin

Research output: Contribution to journalArticle

Abstract

Construct equivalence of measures across studies is necessary for synthesizing results when combining data in meta-analysis or integrative data analysis. We discuss several assumptions required for construct equivalence, and review methods using individual-level data and item response theory (IRT) analysis for detecting or adjusting for violations of these assumptions. We apply IRT to data from 7 measures of depressive symptoms for 4,283 youth from 16 randomized prevention trials. Findings indicate that these data violate assumptions of conditional independence. Bifactor IRT models find that depression measures contain substantial reporter variance, and indicate that a single common factor model would be substantially biased. Separate analyses of ratings by youth find stronger evidence for construct equivalence, but factor invariance across sex and age does not hold. We conclude that data synthesis studies employing measures of youth depression should analyze results separately by reporter, explore more complex approaches to integrate these different perspectives, and explore methods that adjust for sex and age differences in item functioning.

Original languageEnglish (US)
JournalPsychological Assessment
DOIs
StatePublished - Jan 1 2019

Fingerprint

Depression
Sex Characteristics
Meta-Analysis

Keywords

  • Differential item functioning
  • Harmonization
  • Integrative data analysis
  • Measurement
  • Youth depression

ASJC Scopus subject areas

  • Clinical Psychology
  • Psychiatry and Mental health

Cite this

Evaluating Construct Equivalence of Youth Depression Measures Across Multiple Measures and Multiple Studies. / Howe, George W.; Dagne, Getachew A.; Brown, C. Hendricks; Brincks, Ahnalee M.; Beardslee, William; Perrino, Tatiana; Pantin, Hilda.

In: Psychological Assessment, 01.01.2019.

Research output: Contribution to journalArticle

Howe, George W. ; Dagne, Getachew A. ; Brown, C. Hendricks ; Brincks, Ahnalee M. ; Beardslee, William ; Perrino, Tatiana ; Pantin, Hilda. / Evaluating Construct Equivalence of Youth Depression Measures Across Multiple Measures and Multiple Studies. In: Psychological Assessment. 2019.
@article{a1f7cee16af34bc793045ec9506a9f29,
title = "Evaluating Construct Equivalence of Youth Depression Measures Across Multiple Measures and Multiple Studies",
abstract = "Construct equivalence of measures across studies is necessary for synthesizing results when combining data in meta-analysis or integrative data analysis. We discuss several assumptions required for construct equivalence, and review methods using individual-level data and item response theory (IRT) analysis for detecting or adjusting for violations of these assumptions. We apply IRT to data from 7 measures of depressive symptoms for 4,283 youth from 16 randomized prevention trials. Findings indicate that these data violate assumptions of conditional independence. Bifactor IRT models find that depression measures contain substantial reporter variance, and indicate that a single common factor model would be substantially biased. Separate analyses of ratings by youth find stronger evidence for construct equivalence, but factor invariance across sex and age does not hold. We conclude that data synthesis studies employing measures of youth depression should analyze results separately by reporter, explore more complex approaches to integrate these different perspectives, and explore methods that adjust for sex and age differences in item functioning.",
keywords = "Differential item functioning, Harmonization, Integrative data analysis, Measurement, Youth depression",
author = "Howe, {George W.} and Dagne, {Getachew A.} and Brown, {C. Hendricks} and Brincks, {Ahnalee M.} and William Beardslee and Tatiana Perrino and Hilda Pantin",
year = "2019",
month = "1",
day = "1",
doi = "10.1037/pas0000737",
language = "English (US)",
journal = "Psychological Assessment",
issn = "1040-3590",
publisher = "American Psychological Association Inc.",

}

TY - JOUR

T1 - Evaluating Construct Equivalence of Youth Depression Measures Across Multiple Measures and Multiple Studies

AU - Howe, George W.

AU - Dagne, Getachew A.

AU - Brown, C. Hendricks

AU - Brincks, Ahnalee M.

AU - Beardslee, William

AU - Perrino, Tatiana

AU - Pantin, Hilda

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Construct equivalence of measures across studies is necessary for synthesizing results when combining data in meta-analysis or integrative data analysis. We discuss several assumptions required for construct equivalence, and review methods using individual-level data and item response theory (IRT) analysis for detecting or adjusting for violations of these assumptions. We apply IRT to data from 7 measures of depressive symptoms for 4,283 youth from 16 randomized prevention trials. Findings indicate that these data violate assumptions of conditional independence. Bifactor IRT models find that depression measures contain substantial reporter variance, and indicate that a single common factor model would be substantially biased. Separate analyses of ratings by youth find stronger evidence for construct equivalence, but factor invariance across sex and age does not hold. We conclude that data synthesis studies employing measures of youth depression should analyze results separately by reporter, explore more complex approaches to integrate these different perspectives, and explore methods that adjust for sex and age differences in item functioning.

AB - Construct equivalence of measures across studies is necessary for synthesizing results when combining data in meta-analysis or integrative data analysis. We discuss several assumptions required for construct equivalence, and review methods using individual-level data and item response theory (IRT) analysis for detecting or adjusting for violations of these assumptions. We apply IRT to data from 7 measures of depressive symptoms for 4,283 youth from 16 randomized prevention trials. Findings indicate that these data violate assumptions of conditional independence. Bifactor IRT models find that depression measures contain substantial reporter variance, and indicate that a single common factor model would be substantially biased. Separate analyses of ratings by youth find stronger evidence for construct equivalence, but factor invariance across sex and age does not hold. We conclude that data synthesis studies employing measures of youth depression should analyze results separately by reporter, explore more complex approaches to integrate these different perspectives, and explore methods that adjust for sex and age differences in item functioning.

KW - Differential item functioning

KW - Harmonization

KW - Integrative data analysis

KW - Measurement

KW - Youth depression

UR - http://www.scopus.com/inward/record.url?scp=85068226423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068226423&partnerID=8YFLogxK

U2 - 10.1037/pas0000737

DO - 10.1037/pas0000737

M3 - Article

C2 - 31259571

AN - SCOPUS:85068226423

JO - Psychological Assessment

JF - Psychological Assessment

SN - 1040-3590

ER -