Applied Compositional Data Analysis

Templ, Matthias

doi:10.1007/978-3-319-96422-5

Cited by 221 publications

(253 citation statements)

References 0 publications

Supporting

Mentioning

221

Contrasting

Unclassified

Order By: Relevance

“…For the purpose of compositional regression analysis, compositions were mapped into real space using isometric log-ratio (ilr) transformation [29]. Specifically, compositional covariates were expressed through pivot coordinates which enable for interpretation in terms of dominance of a given compositional part with reference to the rest of components in the first coordinate (e.g., ilr 1 ) [30]. For this purpose, the compositional parts were permutated, as explained in detail in previous papers [19,22].…”

Section: Discussionmentioning

confidence: 99%

Sedentary behavior patterns and adiposity in children: a study based on compositional data analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

Background: Between-person differences in sedentary patterns should be considered to understand the role of sedentary behavior (SB) in the development of childhood obesity. This study took a novel approach based on compositional data analysis to examine associations between SB patterns and adiposity and investigate differences in adiposity associated with time reallocation between time spent in sedentary bouts of different duration and physical activity. Methods: An analysis of cross-sectional data was performed in 425 children aged 7-12 years (58% girls). Waking behaviors were assessed using ActiGraph GT3X accelerometer for seven consecutive days. Multi-frequency bioimpedance measurement was used to determine adiposity. Compositional regression models with robust estimators were used to analyze associations between sedentary patterns and adiposity markers. To examine differences in adiposity associated with time reallocation, we used the compositional isotemporal substitution model. Results: Significantly higher fat mass percentage (FM%; β ilr1 = 0.18; 95% CI: 0.01, 0.34; p = 0.040) and visceral adipose tissue (VAT; β ilr1 = 0.37; 95% CI: 0.03, 0.71; p = 0.034) were associated with time spent in middle sedentary bouts in duration of 10-29 min (relative to remaining behaviors). No significant associations were found for short (< 10 min) and long sedentary bouts (≥30 min). Substituting the time spent in total SB with moderate-to-vigorous physical activity (MVPA) was associated with a decrease in VAT. Substituting 1 h/week of the time spent in middle sedentary bouts with MVPA was associated with 2.9% (95% CI: 1.2, 4.6), 3.4% (95% CI: 1.2, 5.5), and 6.1% (95% CI: 2.9, 9.2) lower FM%, fat mass index, and VAT, respectively. Moreover, substituting 2 h/week of time spent in middle sedentary bouts with short sedentary bouts was associated with 3.5% (95% CI: 0.02, 6.9) lower FM%. Conclusions: Our findings suggest that adiposity status could be improved by increasing MVPA at the expense of time spent in middle sedentary bouts. Some benefits to adiposity may also be expected from replacing middle sedentary bouts with short sedentary bouts, that is, by taking standing or activity breaks more often. These findings may help design more effective interventions to prevent and control childhood obesity.

show abstract

Section: Discussionmentioning

confidence: 99%

Sedentary behavior patterns and adiposity in children: a study based on compositional data analysis

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The observations were compositional because the biomass proportions of all plant species in each survey of a subplot summed to one. The estimated values in each survey were therefore transformed into centred logratio coefficients (Filzmoser, Hron, & Templ, ; see Supporting Information S4 for details). Selection was inferred from the difference d i in biomass proportions before and after grazing.…”

Section: Methodsmentioning

confidence: 99%

Choosy grazers: Influence of plant traits on forage selection by three cattle breeds

et al. 2020

View full text Add to dashboard Cite

1. Forage selection by herbivores is a major driver of plant diversity in pasture vegetation. Yet, we know relatively little about how plant traits influence decisions of different herbivore species and breeds to select or avoid a certain plant species on semi-natural pastures.2. We quantified the influence of the traits leaf N and P content, leaf dry matter content (LDMC), specific leaf area (SLA) and physical defence mechanisms on plant species selection for three cattle breeds: high-yielding Angus × Holstein crossbreed, dual-purpose Original Braunvieh and undemanding Highland Cattle. The cattle grazed a series of adjacent paddocks in different alpine pastures. Plant species selection was quantified by assessing the difference in biomass proportions of all plant species in 66 vegetation subplots per breed before and after grazing. Plant traits and indicator values were extracted from the TRY database. Data on 152 plant species were analysed using a local mixed-effects model and a global multivariate hierarchical regression model. 3. Plant traits had a clear impact on forage behaviour. Plants with high SLA, leaf N and P contents were significantly selected, whereas plants with high LDMC (e.g. woody plants) and defence mechanisms (e.g. thistles) were generally avoided. Species with high forage quality indicator values as defined by Briemle et al. (2002) were significantly preferred. More importantly, significant differences between forage behaviour of cattle breeds were detected. Selection by less-productive Highland Cattle was much less influenced by plant traits than the selection by the two higher-yielding breeds. 4. Results indicate a clear impact of plant traits on forage selection and demonstrate breed-specific influences. Highland Cattle (and possibly other robust breeds) graze less selectively and impose less selective exclusion on plants. Thereby, they likely influence plant species composition of pastures in a different way than highyielding breeds, thereby creating a distinct habitat. K E Y W O R D S alpine pastures, Bayesian statistics, cattle breeds, forage selection, plant traits, species diversity | 981 Functional Ecology PAULER Et AL.

show abstract

“…An appropriate normalization or transformation has been performed by one of the two methods: (a) The normalization to a constant row sum of 100 describes the ions counts as percentages of the nine ion species and is preferred for interpretation. (b) A centered log‐ratio (CLR) transformation of X is recommended for compositional data, defined as x CLR [ i, j ] = log ( x [ i, j ] / G [ i ]) with G [ i ] for the geometric mean of all variables of object i. Calculation of G requires values >0; to overcome this problem, x‐values lower than the 0.05 quantile ( q 0.05 , separately for each variable) were replaced by uniformly distributed random numbers between q 0.05 /5 and q 0.05 .…”

Section: Methodsmentioning

confidence: 99%

Section: Spectral Datamentioning

confidence: 99%

Composition of cometary particles collected during two periods of the Rosetta mission: multivariate evaluation of mass spectral data

Вармуза

Filzmoser

Fray

et al. 2020

Journal of Chemometrics

Self Cite

View full text Add to dashboard Cite

The instrument COSIMA (COmetary Secondary Ion Mass Analyzer) onboard of the European Space Agency mission Rosetta collected and analyzed dust particles in the neighborhood of comet 67P/Churyumov‐Gerasimenko. The chemical composition of the particle surfaces was characterized by time‐of‐flight secondary ion mass spectrometry. A set of 2213 spectra has been selected, and relative abundances for CH‐containing positive ions as well as positive elemental ions define a set of multivariate data with nine variables. Evaluation by complementary chemometric techniques shows different compositions of sample groups collected during two periods of the mission. The first period was August to November 2014 (far from the Sun); the second period was January 2015 to February 2016 (nearer to the Sun). The applied data evaluation methods consider the compositional nature of the mass spectral data and comprise robust principal component analysis as well as classification with discriminant partial least squares regression, k‐nearest neighbor search, and random forest decision trees. The results indicate a high importance of the relative abundances of the secondary ions C+ and Fe+ for the group separation and demonstrate an enhanced content of carbon‐containing substances in samples collected in the period with smaller distances to the Sun.

show abstract

Applied Compositional Data Analysis

Cited by 221 publications

References 0 publications

Sedentary behavior patterns and adiposity in children: a study based on compositional data analysis

Sedentary behavior patterns and adiposity in children: a study based on compositional data analysis

Choosy grazers: Influence of plant traits on forage selection by three cattle breeds

Composition of cometary particles collected during two periods of the Rosetta mission: multivariate evaluation of mass spectral data

Contact Info

Product

Resources

About