Estimating Knots and Their Association in Parallel Bilinear Spline Growth Curve Models in the Framework of Individual Measurement Occasions

• Published in: Psychological methods 2022-10, Vol.27 (5), p.703-729
• Main Authors: Liu, Jin, Perera, Robert A.
• Format: Article
• Language: English
• Subjects: Growth Factor; Human; Mathematical Modeling; Mathematics; Measurement; Nonlinear Regression; Reading; Sciences; Simulation
• ISSN: 1082-989X; 1939-1463
• DOI: 10.1037/met0000309

Latent growth curve models with spline functions are flexible and accessible statistical tools for investigating nonlinear change patterns that exhibit distinct phases of development in manifested variables. Among such models, the bilinear spline growth model (BLSGM) is the most straightforward and intuitive but useful. An existing study has demonstrated that the BLSGM allows the knot (or change-point), at which two linear segments join together, to be an additional growth factor other than the intercept and slopes so that researchers can estimate the knot and its variability in the framework of individual measurement occasions. However, developmental processes usually unfold in a joint development where two or more outcomes and their change patterns are correlated over time. As an extension of the existing BLSGM with an unknown knot, this study considers a parallel BLSGM (PBLSGM) for investigating multiple nonlinear growth processes and estimating the knot with its variability of each process as well as the knot-knot association in the framework of individual measurement occasions. We present the proposed model by simulation studies and a real-world data analysis. Our simulation studies demonstrate that the proposed PBLSGM generally estimate the parameters of interest unbiasedly, precisely and exhibit appropriate confidence interval coverage. An empirical example using longitudinal reading scores, mathematics scores, and science scores shows that the model can estimate the knot with its variance for each growth curve and the covariance between two knots. We also provide the corresponding code for the proposed model. Translational Abstract Latent growth curve models are widely used in psychology and education to study complex developmental patterns of change over time. The trajectories of these change patterns usually exhibit distinct segments in the measurements of a studied construct. More importantly, these developmental processes are rarely isolated. This work proposes a novel model to analyze joint development with nonlinear change patterns. Specifically, we consider the linear-linear piecewise functional form for nonlinear trajectories of each construct. By applying this model, we can estimate (a) the average values and variances of the growth factors, including the initial status (i.e., the intercept), the rate-of-change (i.e., the slope) of each linear piece, and the change-point (or the knot) at which the developmental process transits from one st