Modeling longitudinal data is one of the most active areas of research in social, behavioral, and education sciences because only longitudinal research can provide valuable insights into change and causal relationships, which are inherently linked to policy and decision making. Through longitudinal data, researchers can investigate individual development and the difference in the development among individuals. In addition, researchers can study issues about population heterogeneity, important factors that affect the change trajectories, effective interventions, interrelationships among variables, missing data, etc. 

To draw reliable conclusions with a high external validity, researchers often collect and work with large-scale datasets with complex structures and even untraditional formats. Therefore, many analytical challenges have emerged. Without fully taking the complex data structure into account, longitudinal analyses may lead to biased results and incorrect statistical inferences.

Bayesian methods for complex data analysis has gained increasing popularity, mainly because Bayesian statistics has many advantages over traditional frequentist (i.e., non-Bayesian) statistics. For example, they are powerful to estimate complex longitudinal models, can capture the uncertainty of hypothesis, model, and/or parameters through prior and posterior distributions, and handle nonnormal data and missing data relatively easily.