Analysing time-use composition as dependent variables in physical activity and sedentary behaviour research: different compositional data analysis approaches

Abstract

Recently, there has been a paradigm shift from considering physical activity and sedentary behaviour as "independent" risk factors of health to acknowledging their co-dependency and compositional nature. The focus is now on how these behaviours relate to each other rather than viewing them in isolation. Compositional data analysis (CoDA) is a methodology that has been developed specifically for compositional data and the number of publications using CoDA in physical activity and sedentary behaviour research has increased rapidly in the past years. Yet, only a small proportion of the published studies in physical activity and sedentary behaviour research have investigated the time-use composition as dependent variables. This could be related to challenges regarding the interpretation of the results and the lack of guidelines for deciding which statistical approach to use. Therefore, in this paper, four different approaches for analysing the time-use composition as dependent variables are presented and discussed. This paper advocates that the aim of research should guide how the dependent variable is defined and which data analysis approach is selected, and it encourages researchers to consider analysing time-use components as dependent variables in physical activity and sedentary behaviour research.

Keywords: Compositional data analysis; Ilr coordinates; Isometric log-ratio; Outcome.

Fig. 1

Example of sequential binary partition of four movement behaviours, representing time spent sedentary behaviour, light, moderate and vigorous physical activity, contrasted in three coordinates. Note that the partitions results in non-overlapping groups

Fig. 2

Association between age and relative time in movement behaviours based on a linear regression model with absolute time in different behaviours as the dependent variable

Fig. 3

Association between age and relative time in movement behaviours based on a linear regression model with the isometric log-ratio₁ coordinate for A) Sedentary behaviour, B) Light, C) Moderate, D) Vigorous physical activity as the dependent variable

Fig. 4

Association between age and relative time in movement behaviours, where the isometric log-ratio_1 − 3 were separately analysed as the dependent variable in linear regression models

Fig. 5

Association between age and relative time in movement behaviours based on a linear mixed regression model, including the values of isometric log-ratio_1 − 3 coordinate as the dependent variable

Fig. 6

Association between age and relative time in movement behaviours based on three linear regression models, where the dependent variables are balances. The balance coordinates were sedentary behaviour and light physical activity relative to moderate and vigorous physical activity (isometric log-ratio₁), sedentary behaviour relative to light physical activity (isometric log-ratio₂) and moderate physical activity relative to vigorous physical activity (isometric log-ratio₃)