Open AccessA Review of Statistical Analyses on Physical Activity Data Collected from Accelerometers
Author(s) -
Yukun Zhang,
Haocheng Li,
Sarah Kozey Keadle,
Charles E. Matthews,
Raymond J. Carroll
Publication year - 2019
Publication title -
statistics in biosciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.57
H-Index - 14
eISSN - 1867-1772
pISSN - 1867-1764
DOI - 10.1007/s12561-019-09250-6
Subject(s) - accelerometer , raw data , physical activity , computer science , wearable computer , variety (cybernetics) , energy expenditure , biostatistics , data mining , data science , physical medicine and rehabilitation , artificial intelligence , medicine , embedded system , epidemiology , programming language , endocrinology , operating system
Studies for the associations between physical activity and disease risk have been supported by newly developed wearable accelerometer-based devices. These devices record raw activity/movement information in real time on a second-by-second basis and the data can be converted to a variety of summary metrics, such as energy expenditure, sedentary time and moderate-vigorous intensity physical activity. Here we review some of the methods used to analyze the accelerometer data and the R packages that can generate activity related variables from raw data. We also discuss longitudinal data and functional data approaches to perform analyses for various research purposes.