Equivalence of the Mediation, Confounding and Suppression Effect
Prevention SciencePublished 1 December 2000Open access
David P. MacKinnon, Jennifer L. Krull, Chondra M. Lockwood
Citations4,037
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The statistical similarities among mediation, confounding, and suppression are described and methods to determine the confidence intervals for confounding and suppression effects are proposed based on methods developed for mediated effects.
Abstract
This paper describes the statistical similarities among mediation, confounding, and suppression. Each is quantified by measuring the change in the relationship between an independent and a dependent variable after adding a third variable to the analysis. Mediation and confounding are identical statistically and can be distinguished only on conceptual grounds. Methods to determine the confidence intervals for confounding and suppression effects are proposed based on methods developed for mediated effects. Although the statistical estimation of effects and standard errors is the same, there are important conceptual differences among the three types of effects.
Keywords
MathematicsDecision Sciences
Journal of Personality and Social PsychologyThe moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations.
72,132 Citations1986Reuben M. Baron, David A. Kenny
McGraw-Hill Book CompanyStatistical principles in experimental design.
26,927 Citations1962B. J. WINER
Understanding Attitudes and Predicting Social Behavior
26,054 Citations1980Icek Ajzen, Martin Fishbein
Psychology Press eBooksApplied Multiple Regression/Correlation Analysis for the Behavioral Sciences
20,853 Citations2014Patricia Cohen, Patricia Cohen +2 more
Sociological MethodologyAsymptotic Confidence Intervals for Indirect Effects in Structural Equation Models
12,501 Citations1982Michael E. Sobel
Journal of Educational PsychologyEstimating causal effects of treatments in randomized and nonrandomized studies.
9,471 Citations1974Donald B. Rubin
Experimental Design: Procedures for the Behavioral Sciences
8,579 Citations2013Roger E. Kirk
American Educational Research JournalStatistical Theories of Mental Test Scores
8,138 Citations1969William W. Rozeboom, Frederic M. Lord +2 more
Lecture notes in statisticsCausation, Prediction, and Search
4,740 Citations1993Peter Spirtes, Clark Glymour +1 more
The authors axiomatize the connection between causal structure and probabilistic independence, explore several varieties of causal indistinguishability, formulate a theory of manipulation, and develop asymptotically reliable procedures for searching over equivalence classes of causal models.
Evaluation ReviewEstimating Mediated Effects in Prevention Studies
1,967 Citations1993David P. MacKinnon, James H. Dwyer
Assessment of how prevention and intervention programs achieve their effects requires the measurement of intervening or mediating variables hypothesized to represent the causal mechanism by which the prevention program achieves its effects.
EpidemiologyIdentifiability and Exchangeability for Direct and Indirect Effects
1,818 Citations1992James M. Robins, Sander Greenland
It is shown that adjustment for the intermediate variable, which is the most common method of estimating direct effects, can be biased, and that, even in a randomized crossover trial of exposure, direct and indirect effects cannot be separated without special assumptions.
Multivariate Behavioral ResearchA Simulation Study of Mediated Effect Measures
1,698 Citations1995David P. MacKinnon, Ghulam Warsi +1 more
Analytical solutions for point and variance estimators of themediated effect, the ratio of the mediated to the direct effect, and the proportion of the total effect that is mediated were studied with statistical simulations.
American Sociological ReviewThe Decomposition of Effects in Path Analysis
1,447 Citations1975Duane F. Alwin, Robert M. Hauser
Journal of the American Statistical AssociationOn the Exact Variance of Products
1,351 Citations1960Leo A. Goodman
Sociological MethodologySome New Results on Indirect Effects and Their Standard Errors in Covariance Structure Models
1,012 Citations1986Michael E. Sobel
Psychological BulletinThe problem of equivalent models in applications of covariance structure analysis.
883 Citations1993Robert C. MacCallum, Duane T. Wegener +2 more
A study of 53 published applications showed that equivalent models exist routinely, often in large numbers and may often offer substantively meaningful alternative explanations of data.
Oxford University Press eBooksStatistical Analysis of Epidemiologic Data
812 Citations2004Steve Selvin
This well-established text gives readers a clear understanding of the statistical methods that are widely used in epidemiologic research without depending on advanced mathematical or statistical theory.
Educational and Psychological MeasurementA Revised Definition for Suppressor Variables: a Guide To Their Identification and Interpretation
693 Citations1974Anthony J. Conger
Statistics in MedicineStatistical validation of intermediate endpoints for chronic diseases
655 Citations1992Laurence S. Freedman, Barry I. Graubard +1 more
A criterion due to Prentice for the statistical validation of intermediate endpoints for chronic disease, which involves examining in a cohort or intervention study whether an exposure or intervention effect, adjusted for the intermediate endpoint, is reduced to zero is discussed.
Psychological BulletinSuppression situations in psychological research: Definitions, implications, and applications.
553 Citations1991Joseph Tzelgov, Avishai Henik
Estimating the effects of social interventions
538 Citations1981Charles M. Judd, David A. Kenny
Health Education ResearchSchool-based substance abuse prevention: a review of the state of the art in curriculum, 1980–1990
536 Citations1992William B. Hansen
Comprehensive and Social Influence programs are found to be most successful in preventing the onset of substance use.
The Annals of Mathematical StatisticsThe Probability Function of the Product of Two Normally Distributed Variables
525 Citations1947Leo A. Aroian
Clinical Trials
498 Citations1986Curtis L. Meinert
Sociological MethodologyCausal Inference, Path Analysis, and Recursive Structural Equations Models
305 Citations1988Paul W. Holland
PsychometrikaEffect Analysis and Causation in Linear Structural Equation Models
262 Citations1990Michael E. Sobel
Statistics in MedicineThe control of confounding by intermediate variables
243 Citations1989James M. Robins
An estimator is proposed, the extended standardized risk difference, that provides control for confounding by a covariate that is simultaneously a confounder and an intermediate variable on the causal pathway from exposure to disease.
Multivariate Behavioral ResearchChanging a Causal Hypothesis without Changing the Fit: some Rules for Generating Equivalent Path Models
193 Citations1986Ingeborg Stelzl
The problem that very different causal structures may fit the same set of data equally well is discussed, defined as undecidability in principle and four rules are presented showing how equivalent models may be generated.
JAMAEffects of a multidimensional anabolic steroid prevention intervention. The Adolescents Training and Learning to Avoid Steroids (ATLAS) Program
171 Citations1996Linn Goldberg
This AAS prevention program enhanced healthy behaviors, reduced factors that encourage AAS use, and lowered intent to use AAS over the period of 1 year.
Journal of the American Statistical AssociationThe Null Hypothesis Testing Controversy in Psychology
151 Citations1999David H. Krantz
JAMAEffects of a Multidimensional Anabolic Steroid Prevention Intervention
123 Citations1996Linn Goldberg
Applied Psychological MeasurementThe Use of Structural Equation Models in Interpreting Regression Equations Including Suppressor and Enhancer Variables
108 Citations1979Robert M. McFatter
Educational and Psychological MeasurementSuppressor Variables and the Semipartial Correlation Coefficient
84 Citations1978Wayne F. Velicer
Applied Psychological MeasurementLarge Sample Estimators for Standard Errors of Functions of Correlation Coefficients
61 Citations1980Philip Bobko, Angela M. Rieck
The American StatisticianSometimes<i>R</i><sup>2</sup>><i>r</i><sup>2</sup><sub><i>yx</i><sub>1</sub></sub>+<i>r</i><sup>2</sup><sub><i>yx</i><sub>2</sub></sub>: Correlated Variables are Not Always Redundant
53 Citations1987David C. Hamilton
The American StatisticianThe Relationship among Sums of Squares, Correlation Coefficients, and Suppression
35 Citations1997Norean Radke Sharpe, Rosemary A. Roberts