Article
Mathematics, Interdisciplinary Applications
David J. Nott, Max Seah, Luai Al-Labadi, Michael Evans, Hui Khoon Ng, Berthold-Georg Englert
Summary: In Bayesian analysis, combining information from different model components and detecting conflicts between sources of information are crucial. By expanding the prior used for analysis into a larger family of priors and considering a marginal likelihood score statistic, it is possible to gain insights into the nature of conflicts and choose appropriate expansions for sensitive conflict checks. Extensions to hierarchically specified priors and connections with other approaches are considered, with illustrations of implementation in complex situations using two applications.
Article
Biology
Xu Jingxiong, Xu Wei, Laurent Briollais
Summary: A novel statistical approach based on Bayes Factor was proposed for evaluating the association between rare genetic variants and disease outcomes, with Bayesian control of false Discovery Rate for genome-wide inference. Simulation studies showed the new BF statistic outperformed standard methods in case-control studies with moderate sample sizes. The real data application in a lung cancer case-control study found enrichment for RVs in known and novel cancer genes, and using informative prior improved gene discovery compared to noninformative prior.
Article
Psychology, Multidisciplinary
Christoph Koenig
Summary: The study aims to provide a new method for weighting informative prior distributions in Bayesian multiple regression models by combining sources of heterogeneity and a similarity measure ω. Through a comprehensive simulation study, the performance and behavior of the similarity-weighted informative prior distribution are investigated and compared to existing methods. The results offer applied researchers a means to specify accurate informative prior distributions.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Computer Science, Information Systems
Jianhai Zhang, Zhiyong Feng, Yong Su, Meng Xing
Summary: A novel Bayesian covariance representation method is proposed in this paper to address the issues of covariance in action recognition. Experimental results show that this method outperforms state-of-the-art methods in some databases.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2021)
Article
Physics, Multidisciplinary
Valeria Leiva-Yamaguchi, Danilo Alvares
Summary: Models that combine longitudinal and survival outcomes have become popular, but the inferential process can be time-consuming. To reduce complexity while maintaining accuracy, a two-stage strategy is proposed where the longitudinal submodel is first fitted, followed by plugging shared information into the survival submodel.
Article
Statistics & Probability
Leonardo Egidi, Francesco Pauli, Nicola Torelli
Summary: The Bayesian-80 model is composed of a prior-likelihood pair, and a prior-data conflict arises when the prior assigns most of its mass to regions of parameter space with low likelihood. In such cases, an automatic prior elicitation method involving a two-component mixture of diffuse and informative priors is proposed. Through examples, the efficacy of these mixture priors in regression models as a tool for regularization of estimates and retrieval of meaningful inferential conclusions is demonstrated.
CANADIAN JOURNAL OF STATISTICS-REVUE CANADIENNE DE STATISTIQUE
(2022)
Article
Environmental Sciences
Miranda M. Loh, Phillipp Schmidt, Yvette Christopher de Vries, Nina Vogel, Marike Kolossa-Gehring, Jelle Vlaanderen, Erik Lebret, Mirjam Luijten
Summary: In the past, chemical mixture risk assessment has focused on external exposures. This study demonstrates the use of human biomonitoring data to assess the internal concentration of chemicals and their potential health risks. It identifies correlated biomarkers and uses a biomonitoring hazard index to evaluate the health concerns of chemical co-occurrence patterns. The importance rating for this study is 8 out of 10.
Article
Virology
Jeremie Scire, Joelle Barido-Sottani, Denise Kuehnert, Timothy G. Vaughan, Tanja Stadler
Summary: The multi-type birth-death model with sampling is an evolution dynamic model that quantifies past population dynamics in structured populations based on phylogenetic trees, implemented using the bdmm package. Important algorithmic changes to bdmm allows for the analysis of more genetic samples, improving numerical robustness and efficiency, leading to increased precision of parameter estimates, particularly for structured models with a high number of inferred parameters.
Article
Biochemical Research Methods
Hai-Yun Wang, Jian-Ping Zhao, Chun-Hou Zheng, Yan-Sen Su
Summary: The progress of single-cell RNA sequencing has resulted in a large amount of data that is widely used in biomedical research. Existing analysis methods for this data have limitations in capturing the real structure and providing interpretable representations. The newly designed scGMAAE model integrates Bayesian variational inference and adversarial training, enabling it to process large-scale datasets and yield competitive results.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Biochemical Research Methods
Hai-Yun Wang, Jian-Ping Zhao, Chun-Hou Zheng, Yan-Sen Su
Summary: The progress of single-cell RNA sequencing has resulted in a large amount of data, which are widely used in biomedical research. However, the noise in the raw data and the large number of genes present challenges in capturing the real structure and effective information. Existing methods often assume a Gaussian distribution or a low-dimensional nonlinear space for the data, limiting their flexibility and controllability. Additionally, these methods are computationally costly and struggle with large-scale datasets. In this study, a depth generation model called Gaussian mixture adversarial autoencoders is proposed, which assumes different Gaussian distributions for the low-dimensional embeddings of different cell types. This model integrates Bayesian variational inference and adversarial training to provide interpretable latent representations and discover the statistical distribution of cell types. The scGMAAE model demonstrates good controllability, interpretability, and scalability, allowing for efficient processing of large-scale datasets and outperforming existing methods in various analyses.
BRIEFINGS IN BIOINFORMATICS
(2023)
Article
Multidisciplinary Sciences
Zipeng Liu, Yiming Qin, Tian Wu, Justin D. Tubbs, Larry Baum, Timothy Shin Heng Mak, Miaoxin Li, Yan Dora Zhang, Pak Chung Sham
Summary: Mendelian randomization using GWAS summary statistics is a popular method for inferring causal relationships in complex diseases. However, pleiotropy in GWAS poses challenges in selecting valid instrumental variables, potentially leading to invalid inferences. This study introduces a statistical framework called MRCI to estimate reciprocal causation between two phenotypes using genome-scale summary statistics. Simulation and real GWAS data analyses demonstrate the effectiveness of MRCI in detecting causal influences between diseases and risk factors.
NATURE COMMUNICATIONS
(2023)
Article
Management
Mike G. Tsionas
Summary: This article introduces an approach, the adaptive LASSO estimator, to solving technical efficiency problems in stochastic frontier models. The estimator can be seen as the posterior mean of a stochastic frontier model with a special prior, resulting in technically efficient properties. In empirical applications using a dataset of large U.S. banks, the adaptive LASSO outperforms traditional stochastic frontier models.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2023)
Article
Environmental Sciences
Yuxian Wang, Rongming Zhuo, Linlin Xu, Yuan Fang
Summary: Time-series remote sensing images are important in agricultural monitoring. However, most high temporal resolution time-series data have insufficient spatial resolution, which cannot meet the requirement of precision agriculture. Unmixing technique can obtain object abundances with richer spatial information from coarse-resolution images. Temporal unmixing describes the temporal characteristics of different ground objects, and deep learning techniques have achieved promising performance for the unmixing problem.
Article
Automation & Control Systems
Xiaolong Chen, Yi Chai, Qie Liu, Pengfei Huang, Linchuan Fan
Summary: In this paper, a novel Bayesian sparse multiple kernel-based identification method (BSMKM) for multiple-input single-output (MISO) Hammerstein system is proposed. The method represents the nonlinear part and the linear part using basis-function model and finite impulse response model respectively and estimates all unknown model parameters through hierarchical prior distribution and full Bayesian method based on variational Bayesian inference.
Article
Computer Science, Artificial Intelligence
Haohui Wang, Chihao Zhang, Shihua Zhang
Summary: Matrix decomposition methods in this paper model noise as a mixture of Gaussian distribution, combining robust loss functions and Bayesian priors, while applying Laplace prior on the basis matrix for sparsity and Dirichlet prior on the coefficient matrix for interpretability. Extensive experiments show the superiority of this method over competing ones, benefiting from both Bayesian priors and Mixture of Gaussian noise loss.
Article
Rheumatology
A. Tocoian, P. Buchan, H. Kirby, J. Soranson, M. Zamacona, R. Walley, N. Mitchell, E. Esfandiari, F. Wagner, R. Oliver
Article
Pharmacology & Pharmacy
Rosalind J. Walley, Claire L. Smith, Jeremy D. Gale, Phil Woodward
PHARMACEUTICAL STATISTICS
(2015)
Article
Urology & Nephrology
Wim Scheele, Susan Diamond, Jeremy Gale, Valerie Clerin, Nihad Tamimi, Vu Le, Rosalind Walley, Fernando Grover-Paez, Christelle Perros-Huguet, Timothy Rolph, Meguid El Nahas
JOURNAL OF THE AMERICAN SOCIETY OF NEPHROLOGY
(2016)
Article
Pharmacology & Pharmacy
Rosalind Walley, John Sherington, Joe Rastrick, Eric Detrait, Etienne Hanon, Gillian Watt
PHARMACEUTICAL STATISTICS
(2016)
Review
Obstetrics & Gynecology
Nick Pullen, Claire L. Birch, Garry J. Douglas, Qasim Hussain, Ingrid Pruimboom-Brees, Rosalind J. Walley
HUMAN REPRODUCTION UPDATE
(2011)
Article
Public, Environmental & Occupational Health
Jeremy D. Jokinen, Rosalind J. Walley, Michael W. Colopy, Thomas S. Hilzinger, Peter Verdru
Article
Medical Informatics
Jessica Lim, Li Wang, Nicky Best, Jeen Liu, Jiacheng Yuan, Florence Yong, Lanju Zhang, Rosalind Walley, Alice Gosselin, Robert Roebling, Kert Viele
THERAPEUTIC INNOVATION & REGULATORY SCIENCE
(2020)
Review
Medical Informatics
Yodit Seifu, Margaret Gamalo-Siebers, Friederike M-S Barthel, Junjing Lin, Junshan Qiu, Freda Cooner, Shiling Ruan, Rosalind Walley
THERAPEUTIC INNOVATION & REGULATORY SCIENCE
(2020)
Article
Pharmacology & Pharmacy
Rosalind J. Walley, Andrew P. Grieve
Summary: For any decision-making study, it is important to consider the trade-off between type I and II error rates, as well as the context and prior beliefs of the study. When resources are limited, optimizing this trade-off becomes crucial, especially in the case of planned Bayesian statistical analysis.
PHARMACEUTICAL STATISTICS
(2021)
Article
Pharmacology & Pharmacy
Rosalind Walley, Nigel Brayshaw
Summary: Successful innovation in industry involves both developing new statistical methodology and ensuring its successful implementation by enabling applied statisticians to understand and implement the new method. Advocacy and influencing stakeholders are key to gaining acceptance for the new methodology.
PHARMACEUTICAL STATISTICS
(2022)
Article
Chemistry, Medicinal
Siew Kuen Yeap, Rosalind J. Walley, Mike Snarey, Willem P. van Hoorn, Jonathan S. Mason
JOURNAL OF CHEMICAL INFORMATION AND MODELING
(2007)
Article
Multidisciplinary Sciences
TA Clayton, JC Lindon, O Cloarec, H Antti, C Charuel, G Hanton, JP Provost, JL Le Net, D Baker, RJ Walley, JR Everett, JK Nicholson
Review
Mathematical & Computational Biology
CJ Weir, RJ Walley
STATISTICS IN MEDICINE
(2006)
Article
Biochemical Research Methods
Sally-Ann Fancy, Olaf Beckonert, Gareth Darbon, Warren Yabsley, Rosalind Walley, David Baker, George L. Perkins, Frank S. Pullen, Klaus Rumpel
RAPID COMMUNICATIONS IN MASS SPECTROMETRY
(2006)