Bayesian generalized varying coefficient models for longitudinal proportional data with errors-in-covariates

Abstract

This paper is motivated from a neurophysiological study of muscle fatigue, in which biomedical researchers are interested in understanding the time-dependent relationships of handgrip force and electromyography measures. A varying coefficient model is appealing here to investigate the dynamic pattern in the longitudinal data. The response variable in the study is continuous but bounded on the standard unit interval (0, 1) over time, while the longitudinal covariates are contaminated with measurement errors. We propose a generalization of varying coefficient models for the longitudinal proportional data with errorsin-covariates. We describe two estimation methods with penalized splines, which are formalized under a Bayesian inferential perspective. The first method is an adaptation of the popular regression calibration approach. The second method is based on a joint likelihood under the hierarchical Bayesian model. A simulation study is conducted to evaluate the efficacy of the proposed methods under different scenarios. The analysis of the neurophysiological data is presented to demonstrate the use of the methods.

Spatially Varying Coefficient Inequalities: Evaluating How the Impact of Patient Characteristics on Breast Cancer Survival Varies by Location

“…This interaction takes the form of β ( s ) x , where the coefficient β of the explanatory variable x is varying smoothly according to another explanatory variable s , which is generally a continuous variable such as time or space. Numerous authors have studied varying coefficient models and found the model to be flexible and appealing for investigating dynamic patterns in the data [ 6 – 10 ]. The varying coefficient model provides a clearly interpretable approach for modelling the dynamic spatial relationship between the covariate and response variable.…”

Bayesian inferences for beta semiparametric‐mixed models to analyze longitudinal neuroimaging data

“…Since the sample space of FA is naturally restricted to (0, 1), modeling FA with beta distributions becomes an appropriate choice (Ferrari and Cribari‐Neto, ; Wang, ; Wang et al., ). Let us consider the reparameterized beta distribution to model the continuous data observed on (0, 1).…”