Differentiating between mixed-effects and latent-curve approaches to growth modeling

Abstract

In psychology, mixed-effects models and latent-curve models are both widely used to explore growth over time. Despite this widespread popularity, some confusion remains regarding the overlap of these different approaches. Recent articles have shown that the two modeling frameworks are mathematically equivalent in many cases, which is often interpreted to mean that one's choice of modeling framework is merely a matter of personal preference. However, some important differences in estimation and specification can lead to the models producing very different results when implemented in software. Thus, mathematical equivalence does not necessarily equate to practical equivalence in all cases. In this article, we discuss these two common approaches to growth modeling and highlight contexts in which the choice of the modeling framework (and, consequently, the software) can directly impact the model estimates, or in which certain analyses can be facilitated in one framework over the other. We show that, unless the data are pristine, with a large sample size, linear or polynomial growth, and no missing data, and unless the participants have the same number of measurements collected at the same set of time points, one framework is often more advantageous to adopt. We provide several empirical examples to illustrate these situations, as well as ample software code so that researchers can make informed decisions regarding which framework will be the most beneficial and most straightforward for their research interests.

Development of approximate number sense across the elementary school years: A cross‐cultural longitudinal study

“…To answer the third research question, we used the latent class growth approach (LCA) to identify different types of ANS growth trajectories (latent classes). This approach assumes that the estimated sample is not homogenous in the pattern of changes and that there are different latent classes that can differ not only in the intercept and the rate of changes but also in the direction of changes (Jung & Wickrama, ; McNeish & Matta, ). Within this framework, the intercept and the slope were considered as latent variables, whereas manifested measures of the dependent variables at different time points were treated as indicators for these latent variables.…”

The Great Recession and Fertility in Europe: A Sub-national Analysis

“…We used the mixed-effect approach to growth-curve modelling which fits the GCM within a regression framework. This approach is better suited to modelling growth in one observed outcome variable, time-unbalanced data and models with more than two nesting levels than the alternative latent curve approach, usually fitted with structural equation models (Steele 2008;McNeish and Matta 2018). Our GCM originates from the following simple specification:…”

Episodic memory performance in a multi-ethnic longitudinal study of 13,037 elderly

“…In cognitive neuroscience GCMs have been derived using linear mixed effects model (LMEM) or latent curve models (LCM) [ 1 – 4 , 6 – 11 , 15 – 23 ]. LCM uses factor analysis and structural equation models for unobserved outcomes [ 14 , 24 ] and are best suited for complex models with straightforward large data structures [ 25 ]. The flexibility of the LCM approach in incorporating variables with high degree of inter-individual variability (i.e.…”