516 – Biostatistical Literacy: What Medical and Public Health Professionals Need to Know About Statistics
Skew-elliptical Mixed-effects Models with Time-dependent Viral Decay Rates
Yangxin Huang
University of South Florida
Ren Chen
University of South Florida
Mixed-effects models with different time-varying decay rate functions have been proposed for HIV/AIDS studies. However (i) it is not clear which model is more appropriate, and (ii) the model random error is commonly assumed to follow a normal distribution, which may be unrealistic and can obscure important features of within- and among-subject variations. Because asymmetry of HIV viral load data is still noticeable even after transformation, it is important to use a more general distribution family that enables the unrealistic normal assumption to be relaxed. We developed skewed elliptical (SE) Bayesian mixed-effects models by considering the model random error to have an SE distribution. We compared five SE models that have different time varying decay rate functions. For each model, we also contrasted the performance under different model random error assumption such as normal, Student-t, skew-normal or skew-t distribution. The results indicate that the model with a time-varying viral decay rate that has two exponential components is preferred. The models with skew distributions have been shown beneficial in dealing with asymmetric data and provided better fitting to the data than those with symmetric distributions.