A comparison of standard and compositional data analysis in studies addressing group differences in sedentary behavior and physical activity

Abstract

Background: Data on time spent in physical activity, sedentary behavior and sleep during a day is compositional in nature, i.e. they add up to a constant value. Compositional data have fundamentally different properties from unconstrained data in real space, and require other analytical procedures, referred to as compositional data analysis (CoDA). Most physical activity and sedentary behavior studies, however, still apply analytical procedures adapted to data in real space, which can lead to misleading results. The present study describes a comparison of time spent sedentary and in physical activity between age groups and sexes, and investigates the extent to which results obtained by CoDA differ from those obtained using standard analytical procedures.

Methods: Time spent sedentary, standing, and in physical activity (walking/running/stair climbing/cycling) during work and leisure was determined for 1-4 days among 677 blue-collar workers using accelerometry. Differences between sexes and age groups were tested using MANOVA, using both a standard and a CoDA approach based on isometric log-ratio transformed data.

Results: When determining differences between sexes for different activities time at work, the effect size using standard analysis (η² = 0.045, p < 0.001) was 15% smaller than that obtained with CoDA (η² = 0.052, p < 0.001), although both approaches suggested a statistically significant difference. When determining corresponding differences between age groups, CoDA resulted in a 60% larger, and significant, effect size (η² = 0.012, p = 0.02) than that obtained with the standard approach (η² = 0.008, p = 0.07). During leisure, results based on standard (age; η² = 0.007, p = 0.09; sex; η² = 0.052, p < 0.001) and CoDA (age; η² = 0.007, p = 0.09; sex; η² = 0.051, p < 0.001) analyses were similar.

Conclusion: Results and, hence, inferences concerning age and sex-based differences in time spent sedentary and in physical activity at work differed between CoDA and standard analysis. We encourage researchers to use CoDA in similar studies, to adequately account for the compositional nature of data on physical activity and sedentary behavior.

Keywords: Accelerometry; Age; CoDA; CoDA-based MANOVA; Isometric log-ratio; Sex.

Fig. 1

Differences with bootstrap 95% percentile confidence intervals between sexes (left) and age groups (right) in the log-ratio of geometric mean values for sedentary behavior, standing and physical activity. Men/younger was used as the numerator and women/older as the denominator when calculating the log-ratios. Thus, a positive value of the log-ratio indicates that men/younger spent more time in that behavior than women/older workers. A particular behavior is considered significantly different between groups if its confidence interval does not include zero. PA physical activity.

Fig. 2

Geometric mean barplot indicating the time spent sedentary, standing and in physical activity (PA) at work and leisure stratified by sex and age, in terms of differences from the geometric mean value of the entire population. Each bar represents the geometric mean of the specific group (for example men), expressed in terms of a ratio measured on a logarithmic scale (as expressed on the y axis) to the geometric mean of the entire population for each behavior (sedentary, standing and PA). A ratio of 0 reflects that the geometric means of the specific group and the entire population are equal. Positive and negative values show that the group geometric mean is larger and smaller, respectively, than the entire population. On the basis of the log ratios displayed in the figures, the actual ratio of the geometric group mean to the whole group geometric mean can be calculated. For example, the bar corresponding to the woman group is negative (−0.18) for sedentary time at work. This means that, on average, women spend 16% (100-exp of −0.18) less time at work in sedentary behavior than the whole group

Fig. 3

Recruitment process of the participants