A Renewal of Dyadic Structural Equation Modeling With Latent Variables: Clarifications, Methodological Advantages, and New Directions

ABSTRACT Researchers interested in the quantitative analysis of data from dyads must select a preferred statistical framework. In this review, we focus on one option that has seen relatively modest adoption: dyadic structural equation modeling with latent variables. We begin by distinguishing dyadic SEM from alternate, neighboring, and hybridized frameworks, before sharing our view on the unique—and in our opinion, considerable—value‐proposition of the dyadic SEM framework. We then provide some preliminary evidence that dyadic SEM is subordinated in terms of adoption rates versus its competitors, before offering a contextual analysis of why that may have come to be the case. Finally, we conclude with a discussion of future possibilities, some near and accessible and others farther away and more technical, that researchers in the field might pursue (and benefit from) with the help of dyadic SEM with latent variables.