Compositional Data Analysis in Time-Use Epidemiology

2021 ◽  
pp. 383-404
Author(s):  
Dorothea Dumuid ◽  
Željko Pedišić ◽  
Javier Palarea-Albaladejo ◽  
Josep Antoni Martín-Fernández ◽  
Karel Hron ◽  
...  
Keyword(s):  
Data Analysis ◽  
Time Use ◽  
Compositional Data ◽  
Compositional Data Analysis

scholarly journals How Does Time Use Differ between Individuals Who Do More versus Less Foodwork? A Compositional Data Analysis of Time Use in the United Kingdom Time Use Survey 2014–2015

Nutrients ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2280
Author(s):  
Chloe Clifford Astbury ◽  
Louise Foley ◽  
Tarra L. Penney ◽  
Jean Adams
Keyword(s):  
Data Analysis ◽  
Time Use ◽  
Compositional Data ◽  
Unintended Consequences ◽  
Food Preparation ◽  
Compositional Data Analysis ◽  
Personal Care ◽  
Home Food ◽  
Time Use Survey ◽  
Home Food Preparation

Background: Increased time spent on home food preparation is associated with higher diet quality, but a lack of time is often reported as a barrier to this practice. We compared time use in individuals who do more versus less foodwork (tasks required to feed ourselves and our households, including home food preparation). Methods: Cross-sectional analysis of the UK Time Use Survey 2014–15, participants aged 16+ (N = 6143). Time use over 24 h was attributed to seven compositional parts: personal care; sleep; eating; physical activity; leisure screen time; work (paid and unpaid); and socialising and hobbies. Participants were categorised as doing no, ‘some’ (<70 min), or ‘more’ foodwork (≥70 min). We used compositional data analysis to test whether time-use composition varied between these participant groups, determine which of the parts varied between groups, and test for differences across population subgroups. Results: Participants who spent more time on foodwork spent less time on sleep, eating, and personal care and more time on work. Women who did more foodwork spent less time on personal care, socialising, and hobbies, which was not the case for men. Conclusion: Those who seek to encourage home food preparation should be aware of the associations between foodwork and other activities and design their interventions to guard against unintended consequences.

scholarly journals Cross-sectional and prospective associations of sleep, sedentary and active behaviors with mental health in older people: a compositional data analysis from the Seniors-ENRICA-2 study

2021 ◽  
Vol 18 (1) ◽  
Author(s):  
Verónica Cabanas-Sánchez ◽  
Irene Esteban-Cornejo ◽  
Esther García-Esquinas ◽  
Rosario Ortolá ◽  
Ignacio Ara ◽  
...  
Keyword(s):  
Mental Health ◽  
Data Analysis ◽  
Older People ◽  
Time Use ◽  
Compositional Data ◽  
Global Mental Health ◽  
Health Indicators ◽  
Depression Symptoms ◽  
Compositional Data Analysis ◽  
Cross Sectional

Abstract Background Most studies on the effects of sleep, sedentary behavior (SB), and physical activity (PA) on mental health did not account for the intrinsically compositional nature of the time spent in several behaviors. Thus, we examined the cross-sectional and prospective associations of device-measured compositional time in sleep, SB, light PA (LPA) and moderate-to-vigorous PA (MVPA) with depression symptoms, loneliness, happiness, and global mental health in older people (≥ 65 years). Methods Data were taken from the Seniors-ENRICA-2 study, with assessments in 2015–2017 (wave 0) and 2018–2019 (wave 1). Time spent in sleep, SB, LPA and MVPA was assessed by wrist-worn accelerometers. Depression symptoms, loneliness, happiness, and global mental health were self-reported using validated questionnaires. Analyses were performed using a compositional data analysis (CoDA) paradigm and adjusted for potential confounders. Results In cross-sectional analyses at wave 0 (n = 2489), time-use composition as a whole was associated with depression and happiness (all p < 0.01). The time spent in MVPA relative to other behaviors was beneficially associated with depression (γ = -0.397, p < 0.001), loneliness (γ = -0.124, p = 0.017) and happiness (γ = 0.243, p < 0.001). Hypothetically, replacing 30-min of Sleep, SB or LPA with MVPA was beneficially cross-sectionally related with depression (effect size [ES] ranged -0.326 to -0.246), loneliness (ES ranged -0.118 to -0.073), and happiness (ES ranged 0.152 to 0.172). In prospective analyses (n = 1679), MVPA relative to other behaviors at baseline, was associated with favorable changes in global mental health (γ = 0.892, p = 0.049). We observed a beneficial prospective effect on global mental health when 30-min of sleep (ES = 0.521), SB (ES = 0.479) or LPA (ES = 0.755) were theoretically replaced for MVPA. Conclusions MVPA was cross-sectionally related with reduced depression symptoms and loneliness and elevated level of happiness, and prospectively related with enhanced global mental health. Compositional isotemporal analyses showed that hypothetically replacing sleep, SB or LPA with MVPA could result in modest but significantly improvements on mental health indicators. Our findings add evidence to the emerging body of research on 24-h time-use and health using CoDA and suggest an integrated role of daily behaviors on mental health in older people.

scholarly journals Zero problems with compositional data of physical behaviors: a comparison of three zero replacement methods

2020 ◽  
Vol 17 (1) ◽  
Author(s):  
Charlotte Lund Rasmussen ◽  
Javier Palarea-Albaladejo ◽  
Melker Staffan Johansson ◽  
Patrick Crowley ◽  
Matthew Leigh Stevens ◽  
...  
Keyword(s):  
Data Analysis ◽  
Time Use ◽  
Compositional Data ◽  
Real Data ◽  
Compositional Data Analysis ◽  
Accelerometer Data ◽  
Relative Variation ◽  
Physical Behavior ◽  
Complete Dataset ◽  
Log Ratio

Abstract Background Researchers applying compositional data analysis to time-use data (e.g., time spent in physical behaviors) often face the problem of zeros, that is, recordings of zero time spent in any of the studied behaviors. Zeros hinder the application of compositional data analysis because the analysis is based on log-ratios. One way to overcome this challenge is to replace the zeros with sensible small values. The aim of this study was to compare the performance of three existing replacement methods used within physical behavior time-use epidemiology: simple replacement, multiplicative replacement, and log-ratio expectation-maximization (lrEM) algorithm. Moreover, we assessed the consequence of choosing replacement values higher than the lowest observed value for a given behavior. Method Using a complete dataset based on accelerometer data from 1310 Danish adults as reference, multiple datasets were simulated across six scenarios of zeros (5–30% zeros in 5% increments). Moreover, four examples were produced based on real data, in which, 10 and 20% zeros were imposed and replaced using a replacement value of 0.5 min, 65% of the observation threshold, or an estimated value below the observation threshold. For the simulation study and the examples, the zeros were replaced using the three replacement methods and the degree of distortion introduced was assessed by comparison with the complete dataset. Results The lrEM method outperformed the other replacement methods as it had the smallest influence on the structure of relative variation of the datasets. Both the simple and multiplicative replacements introduced higher distortion, particularly in scenarios with more than 10% zeros; although the latter, like the lrEM, does preserve the ratios between behaviors with no zeros. The examples revealed that replacing zeros with a value higher than the observation threshold severely affected the structure of relative variation. Conclusions Given our findings, we encourage the use of replacement methods that preserve the relative structure of physical behavior data, as achieved by the multiplicative and lrEM replacements, and to avoid simple replacement. Moreover, we do not recommend replacing zeros with values higher than the lowest observed value for a behavior.

scholarly journals Compositional Data Analysis in Time-Use Epidemiology: What, Why, How

2020 ◽  
Vol 17 (7) ◽  
pp. 2220 ◽  
Author(s):  
Dorothea Dumuid ◽  
Željko Pedišić ◽  
Javier Palarea-Albaladejo ◽  
Josep Antoni Martín-Fernández ◽  
Karel Hron ◽  
...  
Keyword(s):  
Physical Activity ◽  
Data Analysis ◽  
Sedentary Behavior ◽  
Time Use ◽  
Compositional Data ◽  
Compositional Data Analysis ◽  
Health It ◽  
Future Directions ◽  
The Relationship ◽  
Daily Time

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.

scholarly journals Effects of Two Randomized and Controlled Multi-Component Interventions Focusing On 24-Hour Movement Behavior among Office Workers: A Compositional Data Analysis

2021 ◽  
Vol 18 (8) ◽  
pp. 4191
Author(s):  
Lisa-Marie Larisch ◽  
Emil Bojsen-Møller ◽  
Carla F. J. Nooijen ◽  
Victoria Blom ◽  
Maria Ekblom ◽  
...  
Keyword(s):  
Physical Activity ◽  
Data Analysis ◽  
Cardiorespiratory Fitness ◽  
Leisure Time ◽  
Compositional Data ◽  
Office Workers ◽  
Movement Behavior ◽  
Compositional Data Analysis ◽  
Intervention Effects ◽  
Time In Bed

Intervention studies aiming at changing movement behavior have usually not accounted for the compositional nature of time-use data. Compositional data analysis (CoDA) has been suggested as a useful strategy for analyzing such data. The aim of this study was to examine the effects of two multi-component interventions on 24-h movement behavior (using CoDA) and on cardiorespiratory fitness among office workers; one focusing on reducing sedentariness and the other on increasing physical activity. Office workers (n = 263) were cluster randomized into one of two 6-month intervention groups, or a control group. Time spent in sedentary behavior, light-intensity, moderate and vigorous physical activity, and time in bed were assessed using accelerometers and diaries, both for 24 h in total, and for work and leisure time separately. Cardiorespiratory fitness was estimated using a sub-maximal cycle ergometer test. Intervention effects were analyzed using linear mixed models. No intervention effects were found, either for 24-h behaviors in total, or for work and leisure time behaviors separately. Cardiorespiratory fitness did not change significantly. Despite a thorough analysis of 24-h behaviors using CoDA, no intervention effects were found, neither for behaviors in total, nor for work and leisure time behaviors separately. Cardiorespiratory fitness did not change significantly. Although the design of the multi-component interventions was based on theoretical frameworks, and included cognitive behavioral therapy counselling, which has been proven effective in other populations, issues related to implementation of and compliance with some intervention components may have led to the observed lack of intervention effect.

Sign in / Sign up

Export Citation Format

Share Document