Premium
Modeling Variability in Individual Development: Differences of Degree or Kind?
Author(s) -
Bauer Daniel J.,
Reyes Heathe Luz McNaughton
Publication year - 2010
Publication title -
child development perspectives
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3
H-Index - 71
eISSN - 1750-8606
pISSN - 1750-8592
DOI - 10.1111/j.1750-8606.2010.00129.x
Subject(s) - latent growth modeling , psychology , longitudinal data , growth curve (statistics) , cognitive psychology , multilevel model , interpretation (philosophy) , statistical model , trajectory , degree (music) , econometrics , computer science , data science , developmental psychology , artificial intelligence , machine learning , data mining , mathematics , physics , astronomy , programming language , acoustics
— It is critical to the progress of developmental science that researchers make proper use of statistical models for analyzing individual change over time. Latent curve models, hierarchical linear growth models, group‐based trajectory models, and growth mixture models are increasingly important tools for longitudinal data analysis. To facilitate their understanding and use, this article clarifies similarities and differences between these models, paying particular attention to the assumptions they make about individual development. An example shows how the results and interpretation vary across model types. The discussion centers on reviewing the strengths and limitations of each approach for developmental research.