Testing for Mediating Variables in Management Research: Concerns, Implications, and Alternative Strategies

By J. Shaver. 2005

305 citations recorded by the source corpus.

Subfields: Management Information Systems, Organizational Behavior and Human Resource Management

View Paper: https://www.semanticscholar.org/paper/f8da09d4b7b5693e1d7e5c67fa9e7e4c027f4f33

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Information Systems

In Organizational Behavior and Human Resource Management

Citations in the corpus

Is there a credibility crisis in strategic management research? Evidence on the reproducibility of study findings (2017, methodology): “…descriptive and correlational data are all that is necessary for many analytical tests including analysis of variance (ANOVA), linear regression (LR), t-tests, discriminant analysis, and structural equation modeling (SEM; see Bergh et al., 2017; Boyd et al., 2010; Shaver, 2005, for illustrations).”
Entrepreneurial Finance Meets Organizational Reality: Comparing Investment Practices and Performance of Corporate and Independent Venture Capitalists (2010, unknown): “Because the error term in this regression may be correlated with that in the second step (Shaver, 2005), we use two-stage least squares (2SLS) estimation.”
The Impact of Institutional and Human Resource Distance on International Entry Strategies (2009, background): “Rather, it can be of opposite sign and its statistical significance is not calculated by standard software (also see Ai and Norton, 2003; Shaver, 2005).”
Integrating Implicit and Explicit Social Cognitions for Enhanced Personality Assessment (2007, background): “Correlated errors may be likely to occur in management research because of unmeasured variables (Shaver, 2005), and they can lead to erroneous results when modeling mediation with OLS procedures (Herting, 2002; Shaver, 2005).”
Network Structure, Collaborative Context, and Individual Creativity (2019, methodology): “To resolve this issue, our estimation strategy employs a three-stage least squares model (3SLS) with an instrumental variables approach (Shaver, 2005; Zellner & Theil, 1962).”
From social capital to entrepreneurial orientation: The mediating role of dynamic capabilities (2017, methodology): “Despite the generalized use of the Baron and Kenny methodology to study the significance of mediating effects, previous literature suggests that this method can produce biased and inconsistent estimators derived from the possible existence of correlations between the error terms of the mediation equ”
Stealthy Footsteps to the Boardroom: Executives' Backgrounds, Sophisticated Interpersonal Influence Behavior, and Board Appointments (2010, methodology): “…primary forms of directors’ contributions to board decision making (i.e., monitoring and control behavior and the provision of advice and 3 We conducted this test using a covariance-structure algorithm that permits error terms of equations in the structural model to correlate (see Shaver, 2005).”
Entrepreneurial exit and entrepreneurial engagement (2011, background): “8As a robustness check, we tested for a correlation between unobservables that affect both exit and engagement and whether the direct relationship between exit and engagement would still hold after taking into account such a correlation (Shaver 2005).”
Intragroup conflict as a mediator between cultural diversity and work group outcomes (2007, methodology): “In Baron and Kenny’s (1986) mediation analysis, a violation of this assumption would occur if the residuals of the regression in the first step were correlated with the residuals of the regression in the third step (Shaver, 2005).”
Supervisor ostracism and defensive silence: a differential needs approach (2018, methodology): “We followed the procedure explained by Shaver (2005) for mediation analyses and specified two additional models.”
Constraints, internationalization and growth: A cross-country analysis of European SMEs (2013, background): “If these error terms are correlated (a situation known as ‘‘correlated unobservables’’), researchers must estimate the correlations jointly with relationships between the observed endogenous variables in order to obtain accurate coefficient estimates (Shaver, 2005).”
Mediation Testing in Management Research (2008, unknown): “If used properly, there are also statistical benefits to using SEM (Baron & Kenny, 1986; Cohen et al., 2003; Kenny et al., 1998; Shaver, 2005), which are beyond the scope of this article.”
Can Charisma Be Taught? Tests of Two Interventions (2011, background): “That is, because the treatment dummy does not correlate with the disturbances in Equation 3 to Equation 7 by experimental design, the estimates of Ĉh_new in Equation 3 to Equation 7 are purged from simultaneity, common methods bias, and measurement error, and their causal direction is “locked-in,” p”