Hierarchical Modelling: Hierarchical Linear Models for the Development of Growth Curves: An Example with Body Mass Index in Overweight/Obese Adults

When data are available on multiple individuals measured at multiple time points that may vary in number or inter-measurement interval, hierarchical linear models (HLM) may be an ideal option. The present paper offers an applied tutorial on the use of HLM for developing growth curves depicting natural changes over time. We illustrate these methods with an example of body mass index (BMI; kg=m²) among overweight and obese adults. We modelled among-person variation in BMI growth curves as a function of subjects' baseline characteristics. Specifically, growth curves were modelled with two-level observations, where the first level was each time point of measurement within each individual and the second level was each individual. Four longitudinal databases with measured weight and height met the inclusion criteria and were pooled for analysis: the Framingham Heart Study (FHS); the Multiple Risk Factor Intervention Trial (MRFIT); the National Health and Nutritional Examination Survey I (NHANES-I) and its follow-up study; and the Tecumseh Mortality Follow-up Study (TMFS). Results indicated that significant quadratic patterns of the BMI growth trajectory depend primarily upon a combination of age and baseline BMI. Specifically, BMI tends to increase with time for younger people with relatively moderate obesity (25≤BMI<30) but decrease for older people regardless of degree of obesity. The gradients of these changes are inversely related to baseline BMI and do not substantially depend on gender.