The jagstargets R package: a reproducible workflow framework for Bayesian data analysis with JAGS

AbstractNear infrared spectroscopy is increasingly being used as an economical method to monitor mosquito vector populations in support of disease control. Despite this rise in popularity, strong geographical variation in spectra has proven an issue for generalising predictions from one location to another. Here, we use a functional data analysis approach—which models spectra as smooth curves rather than as a discrete set of points—to develop a method that is robust to geographic heterogeneity. Specifically, we use a penalised generalised linear modelling framework which includes efficient functional representation of spectra, spectral smoothing and regularisation. To ensure better generalisation of model predictions from one training set to another, we use cross-validation procedures favouring smoother representation of spectra. To illustrate the performance of our approach, we collected spectra for field-caught specimens of Anopheles gambiae complex mosquitoes – the most epidemiologically important vector species on the planet – in two sites in Burkina Faso. Using these spectra, we show how models trained on data from one site can successfully classify morphologically identical sibling species in another site, over 250km away. Whilst we apply our framework to species prediction, our unified statistical framework can, alternatively, handle regression analysis (for example, to determine mosquito age) and other types of multinomial classification (for example, to determine infection status). To make our methods readily available for field entomologists, we have created an open-source R package mlevcm. All data used is publicly also available.

Download Full-text

Bayesian data analysis in the phonetic sciences: A tutorial introduction

Journal of Phonetics ◽

10.1016/j.wocn.2018.07.008 ◽

2018 ◽

Vol 71 ◽

pp. 147-161 ◽

Cited By ~ 26

Author(s):

Shravan Vasishth ◽

Bruno Nicenboim ◽

Mary E. Beckman ◽

Fangfang Li ◽

Eun Jong Kong

Keyword(s):

Data Analysis ◽

Bayesian Data Analysis

Download Full-text

Mathematics and Statistics in Anesthesiology

10.2310/anes.18276 ◽

2018 ◽

Author(s):

Daniel Mortlock

Keyword(s):

Probability Theory ◽

Data Analysis ◽

Survey Design ◽

Probability Distributions ◽

Statistical Tests ◽

Real World Data ◽

Mathematical Functions ◽

P Values ◽

Bayesian Data Analysis ◽

Probability And Statistics

Mathematics is the language of quantitative science, and probability and statistics are the extension of classical logic to real world data analysis and experimental design. The basics of mathematical functions and probability theory are summarized here, providing the tools for statistical modeling and assessment of experimental results. There is a focus on the Bayesian approach to such problems (ie, Bayesian data analysis); therefore, the basic laws of probability are stated, along with several standard probability distributions (eg, binomial, Poisson, Gaussian). A number of standard classical tests (eg, p values, the t-test) are also defined and, to the degree possible, linked to the underlying principles of probability theory. This review contains 5 figures, 1 table, and 15 references. Keywords: Bayesian data analysis, mathematical models, power analysis, probability, p values, statistical tests, statistics, survey design

Download Full-text

Applied Bayesian Data Analysis Using State-Space Models

Data Analysis - Studies in Classification, Data Analysis, and Knowledge Organization ◽

10.1007/978-3-642-58250-9_21 ◽

2000 ◽

pp. 259-271

Author(s):

Renate Meyer

Keyword(s):

Data Analysis ◽

State Space ◽

State Space Models ◽

Bayesian Data Analysis

Download Full-text

Bayesian Data Analysis

The SAGE Handbook of Quantitative Methods in Psychology ◽

10.4135/9780857020994.n19 ◽

2012 ◽

pp. 423-443 ◽

Cited By ~ 1

Author(s):

Herbert Hoijtink

Keyword(s):

Data Analysis ◽

Bayesian Data Analysis

Download Full-text

Vertical and horizontal integration of multi-omics data with miodin

BMC Bioinformatics ◽

10.1186/s12859-019-3224-4 ◽

2019 ◽

Vol 20 (1) ◽

Cited By ~ 13

Author(s):

Benjamin Ulfenborg

Keyword(s):

Data Analysis ◽

R Package ◽

Heterogeneous Data ◽

Omics Data ◽

Technical Expertise ◽

Horizontal Integration ◽

Level Data ◽

Genomics And Proteomics ◽

Health And Disease ◽

Molecular Layers

Abstract Background Studies on multiple modalities of omics data such as transcriptomics, genomics and proteomics are growing in popularity, since they allow us to investigate complex mechanisms across molecular layers. It is widely recognized that integrative omics analysis holds the promise to unlock novel and actionable biological insights into health and disease. Integration of multi-omics data remains challenging, however, and requires combination of several software tools and extensive technical expertise to account for the properties of heterogeneous data. Results This paper presents the miodin R package, which provides a streamlined workflow-based syntax for multi-omics data analysis. The package allows users to perform analysis of omics data either across experiments on the same samples (vertical integration), or across studies on the same variables (horizontal integration). Workflows have been designed to promote transparent data analysis and reduce the technical expertise required to perform low-level data import and processing. Conclusions The miodin package is implemented in R and is freely available for use and extension under the GPL-3 license. Package source, reference documentation and user manual are available at https://gitlab.com/algoromics/miodin.

Download Full-text