No abstract

The health effects of daily activity behaviours (physical activity, sedentary time and sleep) are widely studied. While previous research has largely examined activity behaviours in isolation, recent studies have adjusted for multiple behaviours. However, the inclusion of all activity behaviours in traditional multivariate analyses has not been possible due to the perfect multicollinearity of 24-h time budget data. The ensuing lack of adjustment for known effects on the outcome undermines the validity of study findings. We describe a statistical approach that enables the inclusion of all daily activity behaviours, based on the principles of compositional data analysis. Using data from the International Study of Childhood Obesity, Lifestyle and the Environment, we demonstrate the application of compositional multiple linear regression to estimate adiposity from children's daily activity behaviours expressed as isometric log-ratio coordinates. We present a novel method for predicting change in a continuous outcome based on relative changes within a composition, and for calculating associated confidence intervals to allow for statistical inference. The compositional data analysis presented overcomes the lack of adjustment that has plagued traditional statistical methods in the field, and provides robust and reliable insights into the health effects of daily activity behaviours.

How people use their time has been linked with their health. For example, spending more time being physically active is known to be beneficial for health, whereas long durations of sitting have been associated with unfavourable health outcomes. Accordingly, public health messages have advocated swapping strategies to promote the reallocation of time between parts of the time-use composition, such as "Move More, Sit Less", with the aim of achieving optimal distribution of time for health. However, the majority of research underpinning these public health messages has not considered daily time use as a composition, and has ignored the relative nature of time-use data. We present a way of applying compositional data analysis to estimate change in a health outcome when fixed durations of time are reallocated from one part of a particular time-use composition to another, while the remaining parts are kept constant, based on a multiple linear regression model on isometric log ratio coordinates. In an example, we examine the expected differences in Body Mass Index z-scores for reallocations of time between sleep, physical activity and sedentary behaviour.

In recent years, the focus of activity behavior research has shifted away from univariate paradigms (e.g., physical activity, sedentary behavior and sleep) to a 24-h time-use paradigm that integrates all daily activity behaviors. Behaviors are analyzed relative to each other, rather than as individual entities. Compositional data analysis (CoDA) is increasingly used for the analysis of time-use data because it is intended for data that convey relative information. While CoDA has brought new understanding of how time use is associated with health, it has also raised challenges in how this methodology is applied, and how the findings are interpreted. In this paper we provide a brief overview of CoDA for time-use data, summarize current CoDA research in time-use epidemiology and discuss challenges and future directions. We use 24-h time-use diary data from Wave 6 of the Longitudinal Study of Australian Children (birth cohort, n = 3228, aged 10.9 ± 0.3 years) to demonstrate descriptive analyses of time-use compositions and how to explore the relationship between daily time use (sleep, sedentary behavior and physical activity) and a health outcome (in this example, adiposity). We illustrate how to comprehensively interpret the CoDA findings in a meaningful way.

Compositional count data are discrete vectors representing the numbers of outcomes falling into any of several mutually exclusive categories. Compositional techniques based on the log-ratio methodology are appropriate in those cases where the total sum of the vector elements is not of interest. Such compositional count data sets can contain zero values which are often the result of insufficiently large samples. That is, they refer to unobserved positive values that may have been observed with a larger number of trials or with a different sampling design. Because the log-ratio transformations require data with positive values, any statistical analysis of count compositions must be preceded by a proper replacement of the zeros. A Bayesian-multiplicative treatment has been proposed for addressing this count zero problem in several case studies. This treatment involves the Dirichlet prior distribution as the conjugate distribution of the multinomial distribution and a multiplicative modification of the non-zero values. Different parameterizations of the prior distribution provide different zero replacement results, whose coherence with the vector space structure of the simplex is stated. Their performance is evaluated from both the theoretical and the computational point of viewThis research was supported by the Ministerio de Economia y Competividad under the project 'METRICS' Ref. MTM2012-33236, by the Agencia de Gestio d'Ajuts Universitaris i de Recerca of the Generalitat de Catalunya under the project Ref: 2009SGR424, and by the Scottish Government's Rural and Environment Science and Analytical Services Division (RESAS). The authors also gratefully acknowledge the support by the Operational Program Education for Competitiveness-European Social Fund (project CZ.1.07/2.3.00/20.0170 of the Ministry of Education, Youth and Sports of the Czech Republic