Hock-Peng Sin

Understanding why they don't see eye to eye: an examination of leader-member exchange (LMX) agreement.

Although it is an explicitly dyadic approach to leadership, some leader-member exchange (LMX) research has been characterized by relatively low levels of agreement between leader and member judgments of the relationship. Using a combination of meta-analytic methods and primary data collection, the authors sought to explore several theoretically and methodologically meaningful factors that might account for lower levels of agreement. On the basis of data from 64 independent samples (N = 10,884 dyads), the authors found that overall agreement was moderate in nature (? = .37). In addition, they found that longer relationship tenure, affectively oriented relationship dimensions, and ad hoc sampling techniques showed the highest levels of agreement. Empirical results from 98 matched dyads revealed that the extent of LMX agreement increases as the length of relationship tenure and intensity of dyadic interaction increases. Implications for LMX theory and future empirical research are discussed.

How Do Missing Data Bias Estimates of Within-Group Agreement? Sensitivity of SDWG, CVWG, rWG(J), rWG(J) ∗ , and ICC to Systematic Nonresponse

In multilevel theory testing, estimation of group-level properties (i.e., consensus and diversity) is often complicated by missing data. Researchers are left to draw inferences about group constructs (e.g., organizational climate and climate strength) from the responses of only a subset of group members. This study analyzes the biasing impact of random and non-random missingness patterns on within-group agreement and reliability (standard deviation, coefficient of variation, rWG(J), r* WG(J), ADM, aWG , and intraclass correlation) across a range of response rates, numbers of items, and systematic missing data mechanisms. Results demonstrate biases up to 20% over- or underestimation for common response rates found in organizational research. Correction formulae are presented, which enable assessment of the sensitivity of multilevel results to survey nonresponse.

Knowledge Management Processes and Work Group Innovation.

Abstract: Following a selective review of theoretical models and empirical research on work group effectiveness and innovation, we present a dynamic model of work group innovation. Our model integrates recent advances in taxonomies of work group processes and stages of the innovation process with a focus on the temporal nature of innovation. We also provide a discussion of the specific inputs, group processes, emergent states, and outcomes that appear to be most relevant for each of the various stages of work group innovation.

Small sample mediation testing: misplaced confidence in bootstrapped confidence intervals.

Bootstrapping is an analytical tool commonly used in psychology to test the statistical significance of the indirect effect in mediation models. Bootstrapping proponents have particularly advocated for its use for samples of 20-80 cases. This advocacy has been heeded, especially in the Journal of Applied Psychology, as researchers are increasingly utilizing bootstrapping to test mediation with samples in this range. We discuss reasons to be concerned with this escalation, and in a simulation study focused specifically on this range of sample sizes, we demonstrate not only that bootstrapping has insufficient statistical power to provide a rigorous hypothesis test in most conditions but also that bootstrapping has a tendency to exhibit an inflated Type I error rate. We then extend our simulations to investigate an alternative empirical resampling method as well as a Bayesian approach and demonstrate that they exhibit comparable statistical power to bootstrapping in small samples without the associated inflated Type I error. Implications for researchers testing mediation hypotheses in small samples are presented. For researchers wishing to use these methods in their own research, we have provided R syntax in the online supplemental materials.

Leader–Member Exchange (LMX) Measurement: Evidence for Consensus, Construct Breadth, and Discriminant Validity

Purpose – This chapter (a) summarizes leader–member exchange (LMX) measurement practices since the influential reviews by Schriesheim, Castro, and Cogliser (1999) and Gerstner and Day (1997), (b) clarifies the status of LMX as a broad construct from a hierarchical factor model, (c) conducts multitrait-multimethod (MTMM) analyses on leader and follower reports of multidimensional LMX, and (d) investigates discriminant validity between Member LMX and satisfaction with supervisor. Methodology/Approach – We used (a) a literature search of LMX measurement practices, (b) a combination of meta-analysis and factor analysis to specify the broad LMX construct underlying Liden and Maslyns (1998) (LMX-MDM) multidimensional instrument, (c) MTMM analyses of leader and member ratings of the LMX-MDM, and (d) a combination of meta-analysis and multiple regression to assess incremental validity of Member LMX beyond satisfaction with supervisor. Findings – Since 1999, 85% of LMX studies now use one of two dominant LMX scales (LMX-7, Scandura, & Graen, 1984; LMX-MDM, Liden & Maslyn, 1998). These two measures are correlated (rcorrected=.9), suggesting the LMX-7 and the LMX-MDM are alternate forms of the same instrument. 94% of studies that used these two measures treat LMX as a single, broad construct rather than as a multidimensional set of constructs. MTMM analyses suggest Leader LMX and Member LMX are two, separate-but-related constructs (i.e., confirming two source factors and no lower-order trait factors). Last, Member LMX meta-analytically correlates with satisfaction with supervisor at rcorrected=.8. There is some incremental validity of LMX, but the pattern is inconsistent across samples. Social Implications – We point out that LMX researchers have now moved toward standard measurement of LMX – as a broad, higher-order factor that varies between leader and follower. By doing so, we reveal that the stage is set for cumulative and replicable research on leadership as a dyadic, follower-specific phenomenon. Originality/Value of Paper – Our chapter is the first to reveal consensus in LMX measurement across studies; to summarize the standard treatment of LMX as a single, broad factor; and to apply MTMM analyses to demonstrate separate Leader LMX and Member LMX source factors.

Investigating the Uniqueness and Usefulness of Proactive Personality in Organizational Research: A Meta-Analytic Review

Using meta-analysis (283 effect sizes from 122 studies), we extend prior qualitative and quantitative reviews of research on proactive personality in a number of meaningful ways. First, we examine the discriminant and incremental validity of proactive personality using meta-analytic regression analyses. Our results reveal that more than 50% of variance in proactive personality is unrelated to the Big Five personality traits collectively. Also, proactive personality accounts for unique variance in overall job performance, task performance, and organizational citizenship behaviors, even after controlling for the Big Five personality traits and general mental ability (for overall job performance and task performance). Moreover, we find no subgroup differences in proactive personality, highlighting its potential use in selection contexts. In conclusion, we discuss implications of our findings for research and practice.