Moderated mediation

Last updated

In statistics, moderation and mediation can occur together in the same model. [1] Moderated mediation, also known as conditional indirect effects, [2] occurs when the treatment effect of an independent variable A on an outcome variable C via a mediator variable B differs depending on levels of a moderator variable D. Specifically, either the effect of A on B, and/or the effect of B on C depends on the level of D.

Contents

Langfred (2004) model

Langfred (2004) was the first to provide a comprehensive treatment of the question of how to conceptualize moderated mediation, classify different types of moderated mediation models, and to develop the logic and methodology for the statistical analysis of such models using multiple regression. [3]

Because there was no established procedure to analyze models with moderated mediation, Langfred (2004) first describes the different types of moderated mediation models that might exist, noting that there are two primary forms of moderated mediation. Type 1, in which the moderator operates on the relationship between the independent variable and the mediator, and Type 2, in which the moderator operates on the relationship between the mediator and the dependent variable. Langfred reviews the existing perspectives on moderated mediation (James and Brett, 1984), [4] and notes that an accepted statistical approach already exists for Type 1 moderated mediation, as demonstrated by Korsgaard, Brodt, and Whitener (2002). [5] Type 2 moderation, however, is more statistically difficult, so Langfred reviews three different possible approaches for the analysis, and ultimately recommends one of them as the correct technique.

A conceptual diagram that depicts a conditional process model that combines simple mediation with moderation of the indirect effect of A on the mediator B. Conditional Process Model.pdf
A conceptual diagram that depicts a conditional process model that combines simple mediation with moderation of the indirect effect of A on the mediator B.
Moderated mediation Moderated mediation.png
Moderated mediation

Langfred (2004) is often overlooked because the academic paper itself is not about statistical methodology. Rather, because the model in the paper involved moderated mediation, a very large appendix was included, in which the definitions and procedures for the regression analysis were developed.

Muller, Judd, & Yzerbyt (2005)

A conceptual diagram representing moderation of a specific indirect effect in parallel multiple mediator model Moderation of a Specific Indirect Effect in a Parallel Multiple Mediator Model.jpg
A conceptual diagram representing moderation of a specific indirect effect in parallel multiple mediator model
A Conceptual Diagram: Moderation of the Direct and Indirect Effects Moderation of the Direct and Indirect Effects.png
A Conceptual Diagram: Moderation of the Direct and Indirect Effects

Muller, Judd, and Yzerbyt (2005) provided additional clarity and definition of moderated mediation. [1] The following regression equations are fundamental to their model of moderated mediation, where A = independent variable, C = outcome variable, B = mediator variable, and D = moderator variable.

C = β40 + β41A + β42D + β43AD + ε4

This equation assesses moderation of the overall treatment effect of A on C.

B = β50 + β51A + β52D + β53AD + ε5

This equation assesses moderation of the treatment effect of A on the mediator B.

C = β60 + β61A + β62D + β63AD + β64B + β65BD + ε6

This equation assesses moderation of the effect of the mediator B on C, as well as moderation of the residual treatment effect of A on C.

Model for the conditional relative indirect and direct effects Moderated Mediation.png
Model for the conditional relative indirect and direct effects

This fundamental equality exists among these equations:

β43 – β63 = β64β53 + β65β51

In order to have moderated mediation, there must be an overall treatment effect of A on the outcome variable C (β41), which does not depend on the moderator (β43 = 0). In addition, the treatment effect of A on the mediator B depends on the moderator (β53 ≠ 0) and/or the effect of the mediator B on the outcome variable C depends on the moderator (β65 ≠ 0).

At least one of the products on the right side of the above equation must not equal 0 (i.e. either β53 ≠ 0 and β64 ≠ 0, or β65 ≠ 0 and β51 ≠ 0). As well, since there is no overall moderation of the treatment effect of A on the outcome variable C (β43 = 0), this means that β63 cannot equal 0. In other words, the residual direct effect of A on the outcome variable C, controlling for the mediator, is moderated.

Additions by Preacher, Rucker, and Hayes (2007)

Conceptual diagram of a moderated mediation process model where the independent variable (A) moderates its own indirect effect on the outcome variable (C) through the mediator (B) by moderating the effect of B on C. Moderated mediation where X moderates the effect of M on Y.jpg
Conceptual diagram of a moderated mediation process model where the independent variable (A) moderates its own indirect effect on the outcome variable (C) through the mediator (B) by moderating the effect of B on C.
Conceptual diagram of a moderated mediation process model in which one variable (D) moderates the relationship between the independent variable (A) and the mediator variable (B) and a second variable (E) moderates the relationship between the mediator variable (B) and the outcome variable (C). Conditional Process with 2 Moderators.jpg
Conceptual diagram of a moderated mediation process model in which one variable (D) moderates the relationship between the independent variable (A) and the mediator variable (B) and a second variable (E) moderates the relationship between the mediator variable (B) and the outcome variable (C).

In addition to the three manners proposed by Muller and colleagues in which moderated mediation can occur, Preacher, Rucker, and Hayes (2007) proposed that the independent variable A itself can moderate the effect of the mediator B on the outcome variable C. They also proposed that a moderator variable D could moderate the effect of A on B, while a different moderator E moderates the effect of B on C. [2]

Differences between moderated mediation and mediated moderation

Moderated mediation relies on the same underlying models (specified above) as mediated moderation. The main difference between the two processes is whether there is overall moderation of the treatment effect of A on the outcome variable C. If there is, then there is mediated moderation. If there is no overall moderation of A on C, then there is moderated mediation. [1]

Testing for moderated mediation

In order to test for moderated mediation, some recommend examining a series of models, sometimes called a piecemeal approach, and looking at the overall pattern of results. [1] This approach is similar to the Baron and Kenny method for testing mediation by analyzing a series of three regressions. [6] These researchers claim that a single overall test would be insufficient to analyze the complex processes at play in moderated mediation, and would not allow one to differentiate between moderated mediation and mediated moderation.

Bootstrapping has also been suggested as a method of estimating the sampling distributions of a moderated mediation model in order to generate confidence intervals. [2] This method has the advantage of not requiring that any assumptions be made about the shape of the sampling distribution.

A conceptual diagram of a conditional process model with a multicategorical antecedent X with 3 categories. Conceptual Model of Conditional Process Analysis with Multicategorical Antecedent.png
A conceptual diagram of a conditional process model with a multicategorical antecedent X with 3 categories.
Moderated Mediation Model with a 3 level Multi-categorical Antecedent Variable Moderated Mediation Model with a 3 level Multi-categorical Antecedent Variable.png
Moderated Mediation Model with a 3 level Multi-categorical Antecedent Variable

Preacher, Rucker and Hayes also discuss an extension of simple slopes analysis for moderated mediation. Under this approach, one must choose a limited number of key conditional values of the moderator that will be examined. As well, one can use the Johnson–Neyman technique to determine the range of significant conditional indirect effects. [2]

Preacher, Rucker, and Hayes (2007) have created an SPSS macro that provides bootstrapping estimations as well as Johnson–Neyman results. Their macro is made obsolete with the release of PROCESS for SPSS and SAS, described in Introduction to Mediation, Moderation, and Conditional Process Analysis (Hayes, 2013) [7]

See also

Related Research Articles

<span class="mw-page-title-main">Psychological statistics</span>

Psychological statistics is application of formulas, theorems, numbers and laws to psychology. Statistical methods for psychology include development and application statistical theory and methods for modeling psychological data. These methods include psychometrics, factor analysis, experimental designs, and Bayesian statistics. The article also discusses journals in the same field.

<span class="mw-page-title-main">Logistic regression</span> Statistical model for a binary dependent variable

In statistics, the logistic model is a statistical model that models the probability of an event taking place by having the log-odds for the event be a linear combination of one or more independent variables. In regression analysis, logistic regression is estimating the parameters of a logistic model. Formally, in binary logistic regression there is a single binary dependent variable, coded by an indicator variable, where the two values are labeled "0" and "1", while the independent variables can each be a binary variable or a continuous variable. The corresponding probability of the value labeled "1" can vary between 0 and 1, hence the labeling; the function that converts log-odds to probability is the logistic function, hence the name. The unit of measurement for the log-odds scale is called a logit, from logistic unit, hence the alternative names. See § Background and § Definition for formal mathematics, and § Example for a worked example.

Analysis of covariance (ANCOVA) is a general linear model which blends ANOVA and regression. ANCOVA evaluates whether the means of a dependent variable (DV) are equal across levels of one or more categorical independent variables and across one or more continuous variables. For example, the categorical variable(s) might describe treatment and the continuous variable(s) might be covariates or nuisance variables; or vice versa. Mathematically, ANCOVA decomposes the variance in the DV into variance explained by the CV(s), variance explained by the categorical IV, and residual variance. Intuitively, ANCOVA can be thought of as 'adjusting' the DV by the group means of the CV(s).

<span class="mw-page-title-main">Dependent and independent variables</span> Concept in mathematical modeling, statistical modeling and experimental sciences

Dependent and independent variables are variables in mathematical modeling, statistical modeling and experimental sciences. Dependent variables are studied under the supposition or demand that they depend, by some law or rule, on the values of other variables. Independent variables, in turn, are not seen as depending on any other variable in the scope of the experiment in question. In this sense, some common independent variables are time, space, density, mass, fluid flow rate, and previous values of some observed value of interest to predict future values.

<span class="mw-page-title-main">Interaction (statistics)</span> Statistical term

In statistics, an interaction may arise when considering the relationship among three or more variables, and describes a situation in which the effect of one causal variable on an outcome depends on the state of a second causal variable. Although commonly thought of in terms of causal relationships, the concept of an interaction can also describe non-causal associations. Interactions are often considered in the context of regression analyses or factorial experiments.

The general linear model or general multivariate regression model is a compact way of simultaneously writing several multiple linear regression models. In that sense it is not a separate statistical linear model. The various multiple linear regression models may be compactly written as

In statistics, econometrics, epidemiology and related disciplines, the method of instrumental variables (IV) is used to estimate causal relationships when controlled experiments are not feasible or when a treatment is not successfully delivered to every unit in a randomized experiment. Intuitively, IVs are used when an explanatory variable of interest is correlated with the error term, in which case ordinary least squares and ANOVA give biased results. A valid instrument induces changes in the explanatory variable but has no independent effect on the dependent variable, allowing a researcher to uncover the causal effect of the explanatory variable on the dependent variable.

In statistics, omitted-variable bias (OVB) occurs when a statistical model leaves out one or more relevant variables. The bias results in the model attributing the effect of the missing variables to those that were included.

Difference in differences is a statistical technique used in econometrics and quantitative research in the social sciences that attempts to mimic an experimental research design using observational study data, by studying the differential effect of a treatment on a 'treatment group' versus a 'control group' in a natural experiment. It calculates the effect of a treatment on an outcome by comparing the average change over time in the outcome variable for the treatment group to the average change over time for the control group. Although it is intended to mitigate the effects of extraneous factors and selection bias, depending on how the treatment group is chosen, this method may still be subject to certain biases.

In statistics, multinomial logistic regression is a classification method that generalizes logistic regression to multiclass problems, i.e. with more than two possible discrete outcomes. That is, it is a model that is used to predict the probabilities of the different possible outcomes of a categorically distributed dependent variable, given a set of independent variables.

Multilevel models are statistical models of parameters that vary at more than one level. An example could be a model of student performance that contains measures for individual students as well as measures for classrooms within which the students are grouped. These models can be seen as generalizations of linear models, although they can also extend to non-linear models. These models became much more popular after sufficient computing power and software became available.

<span class="mw-page-title-main">Causal model</span> Conceptual model in philosophy of science

In the philosophy of science, a causal model is a conceptual model that describes the causal mechanisms of a system. Several types of causal notation may be used in the development of a causal model. Causal models can improve study designs by providing clear rules for deciding which independent variables need to be included/controlled for.

Omnibus tests are a kind of statistical test. They test whether the explained variance in a set of data is significantly greater than the unexplained variance, overall. One example is the F-test in the analysis of variance. There can be legitimate significant effects within a model even if the omnibus test is not significant. For instance, in a model with two independent variables, if only one variable exerts a significant effect on the dependent variable and the other does not, then the omnibus test may be non-significant. This fact does not affect the conclusions that may be drawn from the one significant variable. In order to test effects within an omnibus test, researchers often use contrasts.

<span class="mw-page-title-main">Mediation (statistics)</span> Statistical model

In statistics, a mediation model seeks to identify and explain the mechanism or process that underlies an observed relationship between an independent variable and a dependent variable via the inclusion of a third hypothetical variable, known as a mediator variable. Rather than a direct causal relationship between the independent variable and the dependent variable, a mediation model proposes that the independent variable influences the mediator variable, which in turn influences the dependent variable. Thus, the mediator variable serves to clarify the nature of the relationship between the independent and dependent variables.

In statistics and regression analysis, moderation occurs when the relationship between two variables depends on a third variable. The third variable is referred to as the moderator variable or simply the moderator. The effect of a moderating variable is characterized statistically as an interaction; that is, a categorical or continuous variable that is associated with the direction and/or magnitude of the relation between dependent and independent variables. Specifically within a correlational analysis framework, a moderator is a third variable that affects the zero-order correlation between two other variables, or the value of the slope of the dependent variable on the independent variable. In analysis of variance (ANOVA) terms, a basic moderator effect can be represented as an interaction between a focal independent variable and a factor that specifies the appropriate conditions for its operation.

In statistics, polynomial regression is a form of regression analysis in which the relationship between the independent variable x and the dependent variable y is modelled as an nth degree polynomial in x. Polynomial regression fits a nonlinear relationship between the value of x and the corresponding conditional mean of y, denoted E(y |x). Although polynomial regression fits a nonlinear model to the data, as a statistical estimation problem it is linear, in the sense that the regression function E(y | x) is linear in the unknown parameters that are estimated from the data. For this reason, polynomial regression is considered to be a special case of multiple linear regression.

In statistics and in machine learning, a linear predictor function is a linear function of a set of coefficients and explanatory variables, whose value is used to predict the outcome of a dependent variable. This sort of function usually comes in linear regression, where the coefficients are called regression coefficients. However, they also occur in various types of linear classifiers, as well as in various other models, such as principal component analysis and factor analysis. In many of these models, the coefficients are referred to as "weights".

In statistics, the Sobel test is a method of testing the significance of a mediation effect. The test is based on the work of Michael E. Sobel, a statistics professor at Columbia University in New York, NY, and is an application of the delta method. In mediation, the relationship between the independent variable and the dependent variable is hypothesized to be an indirect effect that exists due to the influence of a third variable. As a result when the mediator is included in a regression analysis model with the independent variable, the effect of the independent variable is reduced and the effect of the mediator remains significant. The Sobel test is basically a specialized t test that provides a method to determine whether the reduction in the effect of the independent variable, after including the mediator in the model, is a significant reduction and therefore whether the mediation effect is statistically significant.

Control functions are statistical methods to correct for endogeneity problems by modelling the endogeneity in the error term. The approach thereby differs in important ways from other models that try to account for the same econometric problem. Instrumental variables, for example, attempt to model the endogenous variable X as an often invertible model with respect to a relevant and exogenous instrument Z. Panel analysis uses special data properties to difference out unobserved heterogeneity that is assumed to be fixed over time.

In statistics, linear regression is a linear approach for modelling the relationship between a scalar response and one or more explanatory variables. The case of one explanatory variable is called simple linear regression; for more than one, the process is called multiple linear regression. This term is distinct from multivariate linear regression, where multiple correlated dependent variables are predicted, rather than a single scalar variable.

References

  1. 1 2 3 4 Muller, D., Judd, C. M., & Yzerbyt, V. Y. (2005). When moderation is mediated and mediation is moderated. Journal of Personality and Social Psychology, 89, 852–863.
  2. 1 2 3 4 Preacher, K. J., Rucker, D. D., & Hayes, A. F. (2007) Addressing moderated mediation hypotheses: Theory, Methods, and Prescriptions. Multivariate Behavioral Research, 42, 185–227.
  3. ↑ Langfred, C. W. 2004. Too much of a good thing? The negative effects of high trust and autonomy in self managing teams. Academy of Management Journal, 47: 385–399.
  4. ↑ James, L. R., & Brett, J. M. 1984. Mediators, moderators, and tests for mediation. Journal of Applied Psychology, 69: 307–321.
  5. ↑ Korsgaard, M. A., Brodt, S. E., & Whitener, E. M. 2002. Trust in the face of conflict: The role of managerial trustworthy behavior and organizational context. Journal of Applied Psychology, 87: 312–319.
  6. ↑ Baron, R. M., & Kenny, D. A. (1986). The moderator-mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51, 1173–1182.
  7. ↑ Hayes. A. F. 2013. Introduction to mediation, moderation, and conditional process analysis: A regression based approach. New York: The Guilford Press.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.