Concealed correlations meta-analysis: A new method for synthesizing standardized regression coefficients

Belén Fernández-Castilla, Ariel M. Aloe, Lies Declercq, Laleh Jamshidi, Patrick Onghena, S. Natasha Beretvas, Wim Van den Noortgate

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The synthesis of standardized regression coefficients is still a controversial issue in the field of meta-analysis. The difficulty lies in the fact that the standardized regression coefficients belonging to regression models that include different sets of covariates do not represent the same parameter, and thus their direct combination is meaningless. In the present study, a new approach called concealed correlations meta-analysis is proposed that allows for using the common information that standardized regression coefficients from different regression models contain to improve the precision of a combined focal standardized regression coefficient estimate. The performance of this new approach was compared with that of two other approaches: (1) carrying out separate meta-analyses for standardized regression coefficients from studies that used the same regression model, and (2) performing a meta-regression on the focal standardized regression coefficients while including an indicator variable as a moderator indicating the regression model to which each standardized regression coefficient belongs. The comparison was done through a simulation study. The results showed that, as expected, the proposed approach led to more accurate estimates of the combined standardized regression coefficients under both random- and fixed-effect models.

Original languageEnglish (US)
Pages (from-to)316-331
Number of pages16
JournalBehavior Research Methods
Volume51
Issue number1
DOIs
StatePublished - Feb 15 2019

Fingerprint

Meta-Analysis
Meta-analysis

Keywords

  • Effect size
  • Meta-analysis
  • Standardized regression coefficients

ASJC Scopus subject areas

  • Experimental and Cognitive Psychology
  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)
  • Psychology (miscellaneous)
  • Psychology(all)

Cite this

Fernández-Castilla, B., Aloe, A. M., Declercq, L., Jamshidi, L., Onghena, P., Natasha Beretvas, S., & Van den Noortgate, W. (2019). Concealed correlations meta-analysis: A new method for synthesizing standardized regression coefficients. Behavior Research Methods, 51(1), 316-331. https://doi.org/10.3758/s13428-018-1123-7

Concealed correlations meta-analysis : A new method for synthesizing standardized regression coefficients. / Fernández-Castilla, Belén; Aloe, Ariel M.; Declercq, Lies; Jamshidi, Laleh; Onghena, Patrick; Natasha Beretvas, S.; Van den Noortgate, Wim.

In: Behavior Research Methods, Vol. 51, No. 1, 15.02.2019, p. 316-331.

Research output: Contribution to journalArticle

Fernández-Castilla, B, Aloe, AM, Declercq, L, Jamshidi, L, Onghena, P, Natasha Beretvas, S & Van den Noortgate, W 2019, 'Concealed correlations meta-analysis: A new method for synthesizing standardized regression coefficients', Behavior Research Methods, vol. 51, no. 1, pp. 316-331. https://doi.org/10.3758/s13428-018-1123-7
Fernández-Castilla, Belén ; Aloe, Ariel M. ; Declercq, Lies ; Jamshidi, Laleh ; Onghena, Patrick ; Natasha Beretvas, S. ; Van den Noortgate, Wim. / Concealed correlations meta-analysis : A new method for synthesizing standardized regression coefficients. In: Behavior Research Methods. 2019 ; Vol. 51, No. 1. pp. 316-331.
@article{a68ea37d3a974feca9fc1477d98b6f60,
title = "Concealed correlations meta-analysis: A new method for synthesizing standardized regression coefficients",
abstract = "The synthesis of standardized regression coefficients is still a controversial issue in the field of meta-analysis. The difficulty lies in the fact that the standardized regression coefficients belonging to regression models that include different sets of covariates do not represent the same parameter, and thus their direct combination is meaningless. In the present study, a new approach called concealed correlations meta-analysis is proposed that allows for using the common information that standardized regression coefficients from different regression models contain to improve the precision of a combined focal standardized regression coefficient estimate. The performance of this new approach was compared with that of two other approaches: (1) carrying out separate meta-analyses for standardized regression coefficients from studies that used the same regression model, and (2) performing a meta-regression on the focal standardized regression coefficients while including an indicator variable as a moderator indicating the regression model to which each standardized regression coefficient belongs. The comparison was done through a simulation study. The results showed that, as expected, the proposed approach led to more accurate estimates of the combined standardized regression coefficients under both random- and fixed-effect models.",
keywords = "Effect size, Meta-analysis, Standardized regression coefficients",
author = "Bel{\'e}n Fern{\'a}ndez-Castilla and Aloe, {Ariel M.} and Lies Declercq and Laleh Jamshidi and Patrick Onghena and {Natasha Beretvas}, S. and {Van den Noortgate}, Wim",
year = "2019",
month = "2",
day = "15",
doi = "10.3758/s13428-018-1123-7",
language = "English (US)",
volume = "51",
pages = "316--331",
journal = "Behavior Research Methods",
issn = "1554-351X",
publisher = "Springer New York",
number = "1",

}

TY - JOUR

T1 - Concealed correlations meta-analysis

T2 - A new method for synthesizing standardized regression coefficients

AU - Fernández-Castilla, Belén

AU - Aloe, Ariel M.

AU - Declercq, Lies

AU - Jamshidi, Laleh

AU - Onghena, Patrick

AU - Natasha Beretvas, S.

AU - Van den Noortgate, Wim

PY - 2019/2/15

Y1 - 2019/2/15

N2 - The synthesis of standardized regression coefficients is still a controversial issue in the field of meta-analysis. The difficulty lies in the fact that the standardized regression coefficients belonging to regression models that include different sets of covariates do not represent the same parameter, and thus their direct combination is meaningless. In the present study, a new approach called concealed correlations meta-analysis is proposed that allows for using the common information that standardized regression coefficients from different regression models contain to improve the precision of a combined focal standardized regression coefficient estimate. The performance of this new approach was compared with that of two other approaches: (1) carrying out separate meta-analyses for standardized regression coefficients from studies that used the same regression model, and (2) performing a meta-regression on the focal standardized regression coefficients while including an indicator variable as a moderator indicating the regression model to which each standardized regression coefficient belongs. The comparison was done through a simulation study. The results showed that, as expected, the proposed approach led to more accurate estimates of the combined standardized regression coefficients under both random- and fixed-effect models.

AB - The synthesis of standardized regression coefficients is still a controversial issue in the field of meta-analysis. The difficulty lies in the fact that the standardized regression coefficients belonging to regression models that include different sets of covariates do not represent the same parameter, and thus their direct combination is meaningless. In the present study, a new approach called concealed correlations meta-analysis is proposed that allows for using the common information that standardized regression coefficients from different regression models contain to improve the precision of a combined focal standardized regression coefficient estimate. The performance of this new approach was compared with that of two other approaches: (1) carrying out separate meta-analyses for standardized regression coefficients from studies that used the same regression model, and (2) performing a meta-regression on the focal standardized regression coefficients while including an indicator variable as a moderator indicating the regression model to which each standardized regression coefficient belongs. The comparison was done through a simulation study. The results showed that, as expected, the proposed approach led to more accurate estimates of the combined standardized regression coefficients under both random- and fixed-effect models.

KW - Effect size

KW - Meta-analysis

KW - Standardized regression coefficients

UR - http://www.scopus.com/inward/record.url?scp=85053818703&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053818703&partnerID=8YFLogxK

U2 - 10.3758/s13428-018-1123-7

DO - 10.3758/s13428-018-1123-7

M3 - Article

C2 - 30251007

AN - SCOPUS:85053818703

VL - 51

SP - 316

EP - 331

JO - Behavior Research Methods

JF - Behavior Research Methods

SN - 1554-351X

IS - 1

ER -