The Relative Trustworthiness of Inferential Tests of the Indirect Effect in Statistical Mediation Analysis: Does Method Really Matter?
- Publication type:
- Journal article
- Metadata:
-
- Autoren
- Andrew F Hayes
- Michael Scharkow
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000325554800005&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.1177/0956797613480187
- eISSN
- 1467-9280
- Externe Identifier
- Clarivate Analytics Document Solution ID: 233GC
- PubMed Identifier: 23955356
- ISSN
- 0956-7976
- Ausgabe der Veröffentlichung
- 10
- Zeitschrift
- PSYCHOLOGICAL SCIENCE
- Schlüsselwörter
- mediation analysis
- indirect effects
- bootstrapping
- Sobel test
- statistical analyses
- hypothesis testing
- Paginierung
- 1918 - 1927
- Datum der Veröffentlichung
- 2013
- Status
- Published
- Titel
- The Relative Trustworthiness of Inferential Tests of the Indirect Effect in Statistical Mediation Analysis: Does Method Really Matter?
- Sub types
- Article
- Ausgabe der Zeitschrift
- 24
Data source: Web of Science (Lite)
- Other metadata sources:
-
- Abstract
- <jats:p>A content analysis of 2 years of Psychological Science articles reveals inconsistencies in how researchers make inferences about indirect effects when conducting a statistical mediation analysis. In this study, we examined the frequency with which popularly used tests disagree, whether the method an investigator uses makes a difference in the conclusion he or she will reach, and whether there is a most trustworthy test that can be recommended to balance practical and performance considerations. We found that tests agree much more frequently than they disagree, but disagreements are more common when an indirect effect exists than when it does not. We recommend the bias-corrected bootstrap confidence interval as the most trustworthy test if power is of utmost concern, although it can be slightly liberal in some circumstances. Investigators concerned about Type I errors should choose the Monte Carlo confidence interval or the distribution-of-the-product approach, which rarely disagree. The percentile bootstrap confidence interval is a good compromise test.</jats:p>
- Autoren
- Andrew F Hayes
- Michael Scharkow
- DOI
- 10.1177/0956797613480187
- eISSN
- 1467-9280
- ISSN
- 0956-7976
- Ausgabe der Veröffentlichung
- 10
- Zeitschrift
- Psychological Science
- Sprache
- en
- Online publication date
- 2013
- Paginierung
- 1918 - 1927
- Datum der Veröffentlichung
- 2013
- Status
- Published
- Herausgeber
- SAGE Publications
- Herausgeber URL
- http://dx.doi.org/10.1177/0956797613480187
- Datum der Datenerfassung
- 2024
- Titel
- The Relative Trustworthiness of Inferential Tests of the Indirect Effect in Statistical Mediation Analysis
- Ausgabe der Zeitschrift
- 24
Data source: Crossref
- Abstract
- A content analysis of 2 years of Psychological Science articles reveals inconsistencies in how researchers make inferences about indirect effects when conducting a statistical mediation analysis. In this study, we examined the frequency with which popularly used tests disagree, whether the method an investigator uses makes a difference in the conclusion he or she will reach, and whether there is a most trustworthy test that can be recommended to balance practical and performance considerations. We found that tests agree much more frequently than they disagree, but disagreements are more common when an indirect effect exists than when it does not. We recommend the bias-corrected bootstrap confidence interval as the most trustworthy test if power is of utmost concern, although it can be slightly liberal in some circumstances. Investigators concerned about Type I errors should choose the Monte Carlo confidence interval or the distribution-of-the-product approach, which rarely disagree. The percentile bootstrap confidence interval is a good compromise test.
- Addresses
- 1School of Communication, The Ohio State University.
- Autoren
- Andrew F Hayes
- Michael Scharkow
- DOI
- 10.1177/0956797613480187
- eISSN
- 1467-9280
- Externe Identifier
- PubMed Identifier: 23955356
- Open access
- false
- ISSN
- 0956-7976
- Ausgabe der Veröffentlichung
- 10
- Zeitschrift
- Psychological science
- Schlüsselwörter
- Humans
- Confidence Intervals
- Data Interpretation, Statistical
- Monte Carlo Method
- Statistics as Topic
- Sprache
- eng
- Medium
- Print-Electronic
- Online publication date
- 2013
- Paginierung
- 1918 - 1927
- Datum der Veröffentlichung
- 2013
- Status
- Published
- Datum der Datenerfassung
- 2013
- Titel
- The relative trustworthiness of inferential tests of the indirect effect in statistical mediation analysis: does method really matter?
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 24
Data source: Europe PubMed Central
- Abstract
- A content analysis of 2 years of Psychological Science articles reveals inconsistencies in how researchers make inferences about indirect effects when conducting a statistical mediation analysis. In this study, we examined the frequency with which popularly used tests disagree, whether the method an investigator uses makes a difference in the conclusion he or she will reach, and whether there is a most trustworthy test that can be recommended to balance practical and performance considerations. We found that tests agree much more frequently than they disagree, but disagreements are more common when an indirect effect exists than when it does not. We recommend the bias-corrected bootstrap confidence interval as the most trustworthy test if power is of utmost concern, although it can be slightly liberal in some circumstances. Investigators concerned about Type I errors should choose the Monte Carlo confidence interval or the distribution-of-the-product approach, which rarely disagree. The percentile bootstrap confidence interval is a good compromise test.
- Autoren
- Andrew F Hayes
- Michael Scharkow
- Autoren-URL
- https://www.ncbi.nlm.nih.gov/pubmed/23955356
- DOI
- 10.1177/0956797613480187
- eISSN
- 1467-9280
- Ausgabe der Veröffentlichung
- 10
- Zeitschrift
- Psychol Sci
- Schlüsselwörter
- Sobel test
- bootstrapping
- hypothesis testing
- indirect effects
- mediation analysis
- statistical analyses
- Confidence Intervals
- Data Interpretation, Statistical
- Humans
- Monte Carlo Method
- Statistics as Topic
- Sprache
- eng
- Country
- United States
- Paginierung
- 1918 - 1927
- PII
- 0956797613480187
- Datum der Veröffentlichung
- 2013
- Status
- Published
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2014
- Titel
- The relative trustworthiness of inferential tests of the indirect effect in statistical mediation analysis: does method really matter?
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 24
Data source: PubMed
- Beziehungen:
- Property of