A structural equation modeling approach for modeling variability as a latent variable.

Abstract

Drawing upon recent developments in structural equation modeling, the current study presents an analytical framework for addressing research questions in which, rather than focusing on means, it is intraindividual (or intragroup) variability that is of direct research interest. Beyond merely serving as an alternative to existing multilevel modeling approaches, this framework allows for extensions to accommodate a variety of complex research scenarios by parameterizing variability as a latent variable that can in turn be embedded within a broader covariance and mean structure involving other observed and/or latent variables. The estimation procedures and parameter interpretation for the latent random variability models are discussed. The versatility of the proposed methods is demonstrated through four empirical examples. The Mplus, BUGS, and Stan model syntax for the illustrative examples are supplied to facilitate the application of the methods.

Safe Among the Unsafe: Psychological Safety Climate Strength Matters for Team Performance

“…In our statistical models, there are two important aspects that might influence the results: nested data structures (i.e., individuals nested in teams) and the high empirical correlation between team psychological safety and climate strength (0.58). To investigate these two aspects at once, we followed up our first robustness analysis by conducting a structural equation model in which within-team variability (i.e., climate strength) was modeled as a random path coefficient at the between level (Feng & Hancock, 2022). 7 Specifically, we included team psychological safety and team performance at the individual level and utilized the log-transformation approach for modelling the individual level variance as a random variable at the team level (see Feng & Hancock, 2022, Model A).…”

“…To investigate these two aspects at once, we followed up our first robustness analysis by conducting a structural equation model in which within-team variability (i.e., climate strength) was modeled as a random path coefficient at the between level (Feng & Hancock, 2022). 7 Specifically, we included team psychological safety and team performance at the individual level and utilized the log-transformation approach for modelling the individual level variance as a random variable at the team level (see Feng & Hancock, 2022, Model A). To estimate the (cross-level) interaction effect between team psychological safety and climate strength, we used a partial approach in which the effect of team psychological safety on team performance at the individual level was modeled as a function of climate strength at the team level.…”

Variability as a functional marker of second language development in older adult learners

“…In many research and applied settings across the social, behavioral, and health sciences, it has been suggested that it is variability, rather than averages, that is of key interest (Feng & Hancock, 2022;Golino et al, 2022). To our knowledge, this is the first study that has examined inconsistency, dispersion, and variability of L2 development in relation to cognitive functioning and socioaffect in old adulthood; and it is also the first study that has investigated age differences in all three of the defined types of IAV simultaneously.…”

Examining Consistency in Intervention Response With Multiple-Groups Latent Curve Models: A Tutorial

“…In the past years, there has been increasing focus on the examination and manipulation of within-person variability in psychology, for example in the areas of clinical science (e.g., Naragon-Gainey, 2019;Russell et al, 2007), affective science (Houben et al, 2015), and human development (Nesselroade & Molenaar, 2010). Relatedly, new statistical approaches have emerged that enable estimation of within-person variability, including methods for modeling intensive longitudinal data (e.g., GIMME, Beltz & Gates, 2017; and dynamic structural equation models, Grimm & Ram, 2018) and isolating variance parameters as endogenous or exogenous variables in a structural equation model (Feng & Hancock, 2022;McNeish, 2021). Adding to the growing literature on individual variability, the present approach examines between-individuals, within-condition variability in slope estimates and its applications to comparing conditions in a clinical trial.…”