Monte Carlo Confidence Intervals for Complex Functions of Indirect Effects

Davood Tofighi, David Mackinnon

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

One challenge in mediation analysis is to generate a confidence interval (CI) with high coverage and power that maintains a nominal significance level for any well-defined function of indirect and direct effects in the general context of structural equation modeling (SEM). This study discusses a proposed Monte Carlo extension that finds the CIs for any well-defined function of the coefficients of SEM such as the product of k coefficients and the ratio of the contrasts of indirect effects, using the Monte Carlo method. Finally, we conduct a small-scale simulation study to compare CIs produced by the Monte Carlo, nonparametric bootstrap, and asymptotic-delta methods. Based on our simulation study, we recommend researchers use the Monte Carlo method to test a complex function of indirect effects.

Original languageEnglish (US)
Pages (from-to)194-205
Number of pages12
JournalStructural Equation Modeling
Volume23
Issue number2
DOIs
StatePublished - Mar 3 2016

Fingerprint

Structural Equation Modeling
Complex Functions
Monte Carlo method
Confidence interval
Well-defined
confidence
Simulation Study
Nonparametric Bootstrap
Delta Method
Direct Effect
Mediation
Significance level
Asymptotic Methods
Monte Carlo methods
Coefficient
Categorical or nominal
simulation
Coverage
mediation
coverage

Keywords

  • confidence interval
  • mediation analysis
  • Monte Carlo

ASJC Scopus subject areas

  • Modeling and Simulation
  • Decision Sciences(all)
  • Economics, Econometrics and Finance(all)
  • Sociology and Political Science

Cite this

Monte Carlo Confidence Intervals for Complex Functions of Indirect Effects. / Tofighi, Davood; Mackinnon, David.

In: Structural Equation Modeling, Vol. 23, No. 2, 03.03.2016, p. 194-205.

Research output: Contribution to journalArticle

@article{40d872db4b1f4cbb99e583b7132fada1,
title = "Monte Carlo Confidence Intervals for Complex Functions of Indirect Effects",
abstract = "One challenge in mediation analysis is to generate a confidence interval (CI) with high coverage and power that maintains a nominal significance level for any well-defined function of indirect and direct effects in the general context of structural equation modeling (SEM). This study discusses a proposed Monte Carlo extension that finds the CIs for any well-defined function of the coefficients of SEM such as the product of k coefficients and the ratio of the contrasts of indirect effects, using the Monte Carlo method. Finally, we conduct a small-scale simulation study to compare CIs produced by the Monte Carlo, nonparametric bootstrap, and asymptotic-delta methods. Based on our simulation study, we recommend researchers use the Monte Carlo method to test a complex function of indirect effects.",
keywords = "confidence interval, mediation analysis, Monte Carlo",
author = "Davood Tofighi and David Mackinnon",
year = "2016",
month = "3",
day = "3",
doi = "10.1080/10705511.2015.1057284",
language = "English (US)",
volume = "23",
pages = "194--205",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "Psychology Press Ltd",
number = "2",

}

TY - JOUR

T1 - Monte Carlo Confidence Intervals for Complex Functions of Indirect Effects

AU - Tofighi, Davood

AU - Mackinnon, David

PY - 2016/3/3

Y1 - 2016/3/3

N2 - One challenge in mediation analysis is to generate a confidence interval (CI) with high coverage and power that maintains a nominal significance level for any well-defined function of indirect and direct effects in the general context of structural equation modeling (SEM). This study discusses a proposed Monte Carlo extension that finds the CIs for any well-defined function of the coefficients of SEM such as the product of k coefficients and the ratio of the contrasts of indirect effects, using the Monte Carlo method. Finally, we conduct a small-scale simulation study to compare CIs produced by the Monte Carlo, nonparametric bootstrap, and asymptotic-delta methods. Based on our simulation study, we recommend researchers use the Monte Carlo method to test a complex function of indirect effects.

AB - One challenge in mediation analysis is to generate a confidence interval (CI) with high coverage and power that maintains a nominal significance level for any well-defined function of indirect and direct effects in the general context of structural equation modeling (SEM). This study discusses a proposed Monte Carlo extension that finds the CIs for any well-defined function of the coefficients of SEM such as the product of k coefficients and the ratio of the contrasts of indirect effects, using the Monte Carlo method. Finally, we conduct a small-scale simulation study to compare CIs produced by the Monte Carlo, nonparametric bootstrap, and asymptotic-delta methods. Based on our simulation study, we recommend researchers use the Monte Carlo method to test a complex function of indirect effects.

KW - confidence interval

KW - mediation analysis

KW - Monte Carlo

UR - http://www.scopus.com/inward/record.url?scp=84957435808&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957435808&partnerID=8YFLogxK

U2 - 10.1080/10705511.2015.1057284

DO - 10.1080/10705511.2015.1057284

M3 - Article

AN - SCOPUS:84957435808

VL - 23

SP - 194

EP - 205

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

IS - 2

ER -