What is it about?

Researchers in psychology and related disciplines often use longitudinal data to examine the effect of a construct measured at one point in time on another construct measured at a later time point. This article provides guidelines for interpreting the size of these prospective effects. We focused on two frequently used models: the cross-lagged panel model (CLPM) and the random intercept cross-lagged panel model (RI-CLPM). We examined the range of effect sizes reported for these models in a quasi-representative sample of published articles drawn from four subfields of psychology (developmental, social–personality, clinical, and industrial–organizational). Average effect sizes were similar for the CLPM and RI-CLPM and did not differ significantly across subfields. Based on the findings, we recommend that researchers use .03 (small effect), .07 (medium effect), and .12 (large effect) as benchmark values when interpreting the size of cross-lagged effects for both the CLPM and RI-CLPM.

Featured Image

Why is it important?

Cross-lagged models are by far the most commonly used method to test the prospective effect of one construct on another, yet no effect size conventions are available for interpreting cross-lagged effects. Therefore, the goal of this research was to establish empirical benchmarks for small, medium, and large cross-lagged effects.

Read the Original

This page is a summary of: Effect size guidelines for cross-lagged effects., Psychological Methods, June 2022, American Psychological Association (APA), DOI: 10.1037/met0000499.
You can read the full text:

Read

Contributors

The following have contributed to this page