scholarly journals Analysis of relative abundances with zeros on environmental gradients: a multinomial regression model

PeerJ ◽  
2018 ◽  
Vol 6 ◽  
pp. e5643 ◽  
Author(s):  
Fiona Chong ◽  
Matthew Spencer
Keyword(s):  
Data Analysis ◽  
Regression Model ◽  
Compositional Data ◽  
Environmental Gradients ◽  
Compositional Data Analysis ◽  
Multinomial Regression ◽  
Point Count ◽  
Compositional Approach ◽  
Multinomial Regression Model ◽  
Relative Abundances

Ecologists often analyze relative abundances, which are an example of compositional data. However, they have made surprisingly little use of recent advances in the field of compositional data analysis. Compositions form a vector space in which addition and scalar multiplication are replaced by operations known as perturbation and powering. This algebraic structure makes it easy to understand how relative abundances change along environmental gradients. We illustrate this with an analysis of changes in hard-substrate marine communities along a depth gradient. We fit a quadratic multivariate regression model with multinomial observations to point count data obtained from video transects. As well as being an appropriate observation model in this case, the multinomial deals with the problem of zeros, which often makes compositional data analysis difficult. We show how the algebra of compositions can be used to understand patterns in dissimilarity. We use the calculus of simplex-valued functions to estimate rates of change, and to summarize the structure of the community over a vertical slice. We discuss the benefits of the compositional approach in the interpretation and visualization of relative abundance data.

A Logistic Normal Multinomial Regression Model for Microbiome Compositional Data Analysis

Biometrics ◽  
2013 ◽  
Vol 69 (4) ◽  
pp. 1053-1063 ◽  
Author(s):  
Fan Xia ◽  
Jun Chen ◽  
Wing Kam Fung ◽  
Hongzhe Li
Keyword(s):  
Data Analysis ◽  
Regression Model ◽  
Compositional Data ◽  
Compositional Data Analysis ◽  
Multinomial Regression ◽  
Multinomial Regression Model

scholarly journals Analysis of relative abundances on environmental gradients

2018 ◽  
Author(s):  
Fiona Chong ◽  
Matthew Spencer
Keyword(s):  
Compositional Data ◽  
Environmental Gradients ◽  
Compositional Data Analysis ◽  
Depth Gradient ◽  
Negative Numbers ◽  
Marine Communities ◽  
Rates Of Change ◽  
Compositional Approach ◽  
Vertical Slice ◽  
Relative Abundances

Ecologists often analyze relative abundances, which are compositions (sets of non-negative numbers with a fixed sum). However, they have made surprisingly little use of recent advances in the field of compositional data analysis. Compositions form a vector space in which addition and scalar multiplication are replaced by operations known as perturbation and powering. This algebraic structure makes it easy to understand how relative abundances change along environmental gradients. We illustrate this with an analysis of changes in hard-substrate marine communities along a depth gradient. We show how the algebra of compositions can be used to understand patterns in dissimilarity. We use the calculus of simplex-valued functions to estimate rates of change, and to summarize the structure of the community over a vertical slice. We discuss the benefits of the compositional approach in the interpretation and visualization of relative abundance data.

scholarly journals Analysis of relative abundances on environmental gradients

2018 ◽  
Author(s):  
Fiona Chong ◽  
Matthew Spencer
Keyword(s):  
Compositional Data ◽  
Environmental Gradients ◽  
Compositional Data Analysis ◽  
Depth Gradient ◽  
Negative Numbers ◽  
Marine Communities ◽  
Rates Of Change ◽  
Compositional Approach ◽  
Vertical Slice ◽  
Relative Abundances

Ecologists often analyze relative abundances, which are compositions (sets of non-negative numbers with a fixed sum). However, they have made surprisingly little use of recent advances in the field of compositional data analysis. Compositions form a vector space in which addition and scalar multiplication are replaced by operations known as perturbation and powering. This algebraic structure makes it easy to understand how relative abundances change along environmental gradients. We illustrate this with an analysis of changes in hard-substrate marine communities along a depth gradient. We show how the algebra of compositions can be used to understand patterns in dissimilarity. We use the calculus of simplex-valued functions to estimate rates of change, and to summarize the structure of the community over a vertical slice. We discuss the benefits of the compositional approach in the interpretation and visualization of relative abundance data.

scholarly journals Zero-inflated generalized Dirichlet multinomial regression model for microbiome compositional data analysis

Biostatistics ◽  
2018 ◽  
Vol 20 (4) ◽  
pp. 698-713 ◽  
Author(s):  
Zheng-Zheng Tang ◽  
Guanhua Chen
Keyword(s):  
Regression Model ◽  
High Throughput Sequencing ◽  
Compositional Data ◽  
Expectation Maximization Algorithm ◽  
Disease Status ◽  
Compositional Data Analysis ◽  
Multinomial Regression ◽  
Sequencing Technologies ◽  
Multinomial Regression Model ◽  
Generalized Dirichlet

Summary There is heightened interest in using high-throughput sequencing technologies to quantify abundances of microbial taxa and linking the abundance to human diseases and traits. Proper modeling of multivariate taxon counts is essential to the power of detecting this association. Existing models are limited in handling excessive zero observations in taxon counts and in flexibly accommodating complex correlation structures and dispersion patterns among taxa. In this article, we develop a new probability distribution, zero-inflated generalized Dirichlet multinomial (ZIGDM), that overcomes these limitations in modeling multivariate taxon counts. Based on this distribution, we propose a ZIGDM regression model to link microbial abundances to covariates (e.g. disease status) and develop a fast expectation–maximization algorithm to efficiently estimate parameters in the model. The derived tests enable us to reveal rich patterns of variation in microbial compositions including differential mean and dispersion. The advantages of the proposed methods are demonstrated through simulation studies and an analysis of a gut microbiome dataset.

scholarly journals O5A.6 Objectively assessed arm elevation and the course of neck and shoulder pain during a 2-year follow-up: a compositional approach

2019 ◽  
Vol 76 (Suppl 1) ◽  
pp. A42.3-A43
Author(s):  
Suzanne Merkus ◽  
Lars-Kristian Lunde ◽  
Markus Koch ◽  
Stein Knardahl ◽  
Kaj Bo Veiersted
Keyword(s):  
Data Analysis ◽  
Shoulder Pain ◽  
Compositional Data ◽  
Healthcare Personnel ◽  
Compositional Data Analysis ◽  
Compositional Approach ◽  
Neck And Shoulder Pain ◽  
Statistical Analysis Method ◽  
Arm Elevation

PurposeTo use a compositional data analysis approach and objective exposure assessments to study the association between the duration of arm elevation and the course of neck and shoulder pain (NSP) during a 2-year follow-up in physically demanding occupations.MethodsConstruction (n=59) and healthcare (n=59) employees wore accelerometers on the dominant upper-arm during a full working day at baseline. Objective assessments using accelerometers addresses biases found in previous studies that estimate duration of arm elevation with self-reports. At baseline and every 6 months for two years, participants reported on NSP (scale 0–3). Duration of arm elevation within predefined ranges (<30°; 30–60°; ≥60) formed the parts of the composition. Compositional data analysis is a new statistical analysis method within occupational health and it is the correct way of analysing data with a compositional nature. The associations between the relative importance of the duration within the levels of arm elevation and the course of NSP during the 2-year follow-up were estimated with compositional linear mixed models, adjusted for confounders.ResultsIn non-adjusted analyses, only duration arm elevation <30° was associated with NSP at baseline (β = 0.37; p=0.015). Duration arm elevation <30° had a tendency to be associated with an improvement in NSP over the 2-year follow-up (<30°*time (β=-0.07; p=0.089)). Neither duration 30–60° nor ≥60 were associated with the course of NSP during follow-up. After adjusting for confounders, none of the durations of arm elevation were associated with the course of NSP over the 2-year period (<30° and NSP (β = 0.20; p=0.126); <30°*time (β=-0.06; p=0.097)).ConclusionAmong construction and healthcare personnel, duration of working in awkward arm elevation postures was not associated with the course of NSP over a 2-year period. Arm elevation alone, without considering force exertion, may not be sufficient to influence the course of NSP.

scholarly journals Changes in Sedentary Behavior Patterns During the Transition from Childhood to Adolescence and Their Association with Adiposity: A Prospective Study Based on Compositional Data Analysis

2021 ◽  
Author(s):  
Lukáš Rubín ◽  
Aleš Gába ◽  
Jana Pelclová ◽  
Nikola Štefelová ◽  
Lukáš Jakubec ◽  
...  
Keyword(s):  
Data Analysis ◽  
Sedentary Behavior ◽  
Fat Mass ◽  
Compositional Data ◽  
Longitudinal Design ◽  
Pediatric Population ◽  
Compositional Data Analysis ◽  
Compositional Approach ◽  
Sedentary Bouts

Abstract Background: To date, no longitudinal study using a compositional approach has examined sedentary behavior (SB) patterns in relation to adiposity in the pediatric population. Therefore, our aims were to (1) investigate the changes in SB patterns and adiposity from childhood to adolescence, (2) analyze the prospective compositional associations between changes in SB patterns and adiposity, and (3) estimate the changes in adiposity associated with substituting SB with physical activity (PA) of different intensities.Methods: The study presents a longitudinal design with a 5-year follow-up. A total of 88 participants (61% girls) were included in the analysis. PA and SB were monitored for seven consecutive days using a hip-worn accelerometer. Adiposity markers (fat mass percentage [FM%], fat mass index [FMI], and visceral adiposity tissue [VAT]) were assessed using the multi-frequency bioimpedance analysis. The prospective associations were examined using compositional data analysis. Results: Over the follow-up period, the proportion of time spent in total SB increased by 154.8 min/day (p < 0.001). The increase in total SB was caused mainly by an increase in middle and long sedentary bouts, as these SB periods increased by 79.8 min/day and 62 min/day (p < 0.001 for both), respectively. FM%, FMI, and VAT increased by 2.4 percent points, 1.0 kg/m2, and 31.5 cm2 (p < 0.001 for all), respectively. Relative to the remaining movement behaviors, the increase in time spent in middle sedentary bouts was significantly associated with higher FM% (βilr1 = 0.27, 95% confidence interval [CI]: 0.02 to 0.53) at follow-up. Lower VAT by 3.3% (95% CI: 0.8 to 5.7), 3.8% (95% CI: 0.03 to 7.4), 3.9% (95% CI: 0.8 to 6.9), and 3.8% (95% CI: 0.7 to 6.9) was associated with substituting 15 min/week spent in total SB and in short, middle, and long sedentary bouts, respectively, with an equivalent amount of time spent in vigorous PA.Conclusions: This study showed unfavorable changes in SB patterns and adiposity status in the transition from childhood to adolescence. Incorporating high-intensity PA at the expense of SB appears to be an appropriate approach to reduce the risk of excess adiposity in the pediatric population.

Sign in / Sign up

Export Citation Format

Share Document