Investigation of Longitudinal Data Analysis Hierarchical Linear Model and Latent Growth Model Using a Longitudinal Nursing Home Dataset

Abstract

The appropriate use of the data analysis method in a longitudinal design remains controversial in gerontological nursing research. The objective of the current study is to compare statistical approaches between a hierarchical-linear model (HLM) and a latent-growth model (LGM) in random effects, variance explained, growth trajectory, and model fitness. Secondary analysis of longitudinal data was used. Two variables were chosen to demonstrate the comparison between statistical methods. The HLM was superior in addressing unbalanced data in repeated-measures analysis of variance (ANOVA) and multivariate ANOVA because its nested data structure and random effects could be estimated. The LGM had advantages in modeling growth trajectories and model-fit comparisons. Superior to the HLM, the LGM reported more acceptable data fit, reporting a quadratic model, and successfully differentiated between and within components. The current research provides some evidence for applying appropriate statistical methods when addressing longitudinal datasets in gerontological nursing research.