Latent Variable Interactions With Ordered-Categorical Indicators: Comparisons of Unconstrained Product Indicator and Latent Moderated Structural Equations Approaches

Methods to handle ordered-categorical indicators in latent variable interactions have been developed, yet they have not been widely applied. This article compares the performance of two popular latent variable interaction modeling approaches in handling ordered-categorical indicators: unconstrained product indicator (UPI) and latent moderated structural equations (LMS). We conducted a simulation study across sample sizes, indicators’ distributions and category conditions. We also studied four strategies to create sets of product indicators for UPI. Results supported using a parceling strategy to create product indicators in the UPI approach or using the LMS approach when the categorical indicators are symmetrically distributed. We applied these models to study the interaction effect between third- to fifth-grade students’ social skills improvement and teacher–student closeness on their state English language arts test scores.

A labor of love? Emotion work in intimate relationships

Drawing on relational developmental systems and gender relations perspectives, this study analyzed data from 1,932 heterosexual couples from Waves 1 and 2 of the German Family Panel to answer three questions: (1) What are the longitudinal associations between male and female partners’ emotion work provision and relationship satisfaction? (2) Are there gender differences in associations between emotion work and relationship satisfaction? (3) Does autonomy moderate associations among these focal variables? An actor–partner interdependence model revealed emotion work was linked to heightened future relationship satisfaction, and female partners’ emotion work was the strongest predictor of both partners’ relationship satisfaction. Latent variable interactions demonstrated male partners’ emotion work was linked to female partners’ heightened relationship satisfaction only when men also reported high levels of autonomy. Emotion work may be a “labor of love” that builds future relationship satisfaction while under the differential “management” of autonomous self-representation and gender norms of affective care.

Integrating Moderation and Mediation

It is increasingly common to test hypotheses combining moderation and mediation. Structural equation modeling (SEM) has been the favored approach to testing mediation hypotheses. However, the biggest challenge to testing moderation hypotheses in SEM was the complexity underlying the modeling of latent variable interactions. We discuss the latent moderated structural equation procedure (LMS) approach to specifying latent variable interactions, which is implemented in Mplus, and offer a simple and accessible way of testing combined moderation and mediation hypotheses using SEM. To do so, we provide sample code for six commonly encountered moderation and mediation cases and relevant equations that can be easily adapted to researchers’ data. By articulating the similarities in the two different approaches, discussing the combination of moderation and mediation, we also contribute to the research methods literature.

The intertwined relationships of power, justice and dependence

Purpose – The purpose of this study, drawing from exchange theory, is to examine how the intertwined relationships between power, justice and relative dependence influence relationship performance in buyer – seller relationships. Design/methodology/approach – A two-wave structural equation model with latent variable interactions was estimated on a dataset of 283 buyer – seller relationships. Findings – Exercised coercive and reward power follow different processes, direct and indirect, to influence relationship performance. The use of coercion was found to be substantively more detrimental to the buyer – seller relationship than the use of rewards were beneficial. Relative dependence tempers the negative influence of coercion. Research limitations/implications – Managers of buyer – seller relationships need to be judicious in their use of coercion and rewards. In their efforts to manage relationship performance, whenever possible, managers should seek to avoid punishing their partner more so than they should seek to reward them. Originality/value – Although proposed under a single theoretical perspective, power and justice have developed as separate streams within the extant literature. Examining these constructs together can increase the current understanding of how to manage buyer – seller relationships.