|
Abstract:
|
Wearable devices, e.g., actigraphies, enable more accurate real-time tracking of a subject's physical activity (PA) level, such as minutes in moderate-to-vigorous intensity PA (MVPA). The intensive within-subject data provided by wearable devices, e.g., minutes in MVPA summarized per hour across multiple days, allow the possibility to model not only the mean PA level, but also the dispersion (variance) level for each subject. Especially in the context of daily PA, subjects' dispersion levels are potentially informative in reflecting their exercise patterns: some subjects might exhibit consistent PA across time and can be considered "less dispersed" subjects; while others might have a large amount of PA at a particular time point, while being sedentary (PA=0) for most of the day, and can be considered "more dispersed" subjects. Thus, we propose a negative binomial mixed effects location-scale model to model these PA counts and to account for the heterogeneity in both the mean and dispersion level across subjects. Further, for the inflated zero counts, we also proposed a hurdle/zero-inflated version which additionally includes the modeling of the probability of having > 0 PA.
|
