arXiv - STAT - Applications最新文献_第7页

Modelling multiplex testing for outbreak Control 为控制疫情建立多重检测模型

arXiv - STAT - Applications Pub Date : 2024-08-30 DOI: arxiv-2408.17239

Martyn Fyles, Christopher E. Overton, Tom Ward, Emma Bennett, Tom Fowler, Ian Hall

{"title":"Modelling multiplex testing for outbreak Control","authors":"Martyn Fyles, Christopher E. Overton, Tom Ward, Emma Bennett, Tom Fowler, Ian Hall","doi":"arxiv-2408.17239","DOIUrl":"https://doi.org/arxiv-2408.17239","url":null,"abstract":"During the SARS-CoV-2 pandemic, polymerase chain reaction (PCR) and lateral\u0000flow device (LFD) tests were frequently deployed to detect the presence of\u0000SARS-CoV-2. Many of these tests were singleplex, and only tested for the\u0000presence of a single pathogen. Multiplex tests can test for the presence of\u0000several pathogens using only a single swab, which can allow for: surveillance\u0000of more pathogens, targeting of antiviral interventions, a reduced burden of\u0000testing, and lower costs. Test sensitivity however, particularly in LFD tests,\u0000is highly conditional on the viral concentration dynamics of individuals. To\u0000inform the use of multiplex testing in outbreak detection it is therefore\u0000necessary to investigate the interactions between outbreak detection strategies\u0000and the differing viral concentration trajectories of key pathogens. Viral\u0000concentration trajectories are estimated for SARS-CoV-2, and Influenza A/B.\u0000Testing strategies for the first five symptomatic cases in an outbreak are then\u0000simulated and used to evaluate key performance indicators. Strategies that use\u0000a combination of multiplex LFD and PCR tests achieve; high levels of detection,\u0000detect outbreaks rapidly, and have the lowest burden of testing across multiple\u0000pathogens. Influenza B was estimated to have lower rates of detection due to\u0000its modelled viral concentration dynamics.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian Inference General Procedures for A Single-subject Test Study 贝叶斯推理单受试者测试研究的一般程序

arXiv - STAT - Applications Pub Date : 2024-08-27 DOI: arxiv-2408.15419

Jie Li, Gary Green, Sarah J. A. Carr, Peng Liu, Jian Zhang

引用次数: 0

Connecting Mass-action Models and Network Models for Infectious Diseases 连接大规模行动模型和传染病网络模型

arXiv - STAT - Applications Pub Date : 2024-08-27 DOI: arxiv-2408.15353

Thien-Minh Le, Jukka-Pekka Onnela

{"title":"Connecting Mass-action Models and Network Models for Infectious Diseases","authors":"Thien-Minh Le, Jukka-Pekka Onnela","doi":"arxiv-2408.15353","DOIUrl":"https://doi.org/arxiv-2408.15353","url":null,"abstract":"Infectious disease modeling is used to forecast epidemics and assess the\u0000effectiveness of intervention strategies. Although the core assumption of\u0000mass-action models of homogeneously mixed population is often implausible, they\u0000are nevertheless routinely used in studying epidemics and provide useful\u0000insights. Network models can account for the heterogeneous mixing of\u0000populations, which is especially important for studying sexually transmitted\u0000diseases. Despite the abundance of research on mass-action and network models,\u0000the relationship between them is not well understood. Here, we attempt to\u0000bridge the gap by first identifying a spreading rule that results in an exact\u0000match between disease spreading on a fully connected network and the classic\u0000mass-action models. We then propose a method for mapping epidemic spread on\u0000arbitrary networks to a form similar to that of mass-action models. We also\u0000provide a theoretical justification for the procedure. Finally, we show the\u0000advantages of the proposed methods using synthetic data that is based on an\u0000empirical network. These findings help us understand when mass-action models\u0000and network models are expected to provide similar results and identify reasons\u0000when they do not.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Inferring ghost cities on the globe in newly developed urban areas based on urban vitality with multi-source data 利用多源数据，根据城市活力推断全球新开发城市地区的鬼城

arXiv - STAT - Applications Pub Date : 2024-08-27 DOI: arxiv-2408.15117

Yecheng Zhang, Tangqi Tu, Ying long

{"title":"Inferring ghost cities on the globe in newly developed urban areas based on urban vitality with multi-source data","authors":"Yecheng Zhang, Tangqi Tu, Ying long","doi":"arxiv-2408.15117","DOIUrl":"https://doi.org/arxiv-2408.15117","url":null,"abstract":"Due to rapid urbanization over the past 20 years, many newly developed areas\u0000have lagged in socio-economic maturity, creating an imbalance with older cities\u0000and leading to the rise of \"ghost cities.\" However, due to the complexity of\u0000socio-economic factors, no global studies have measured this phenomenon. We\u0000propose a unified framework based on urban vitality theory and multi-source\u0000data, validated by various data sources. We derived 8841 natural cities\u0000globally with an area over 5 square kiloxmeters and divided each into new urban\u0000areas (developed after 2005) and old urban areas (developed before 2005). Urban\u0000vitality was gauged using the density of road networks, points of interest\u0000(POIs), and population density with 1 km resolution across morphological,\u0000functional, and social dimensions. By comparing urban vitality in new and old\u0000urban areas, we quantify the ghost cities index (GCI) globally using the theory\u0000of urban vitality for the first time. The results reveal that the vitality of\u0000new urban areas is 7.69% that of old ones. The top 5% (442) of cities were\u0000designated as ghost cities, a finding mirrored by news media and other\u0000research. This study sheds light on strategies for sustainable global\u0000urbanization, crucial for the United Nations' Sustainable Development Goals.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LLOT: application of Laplacian Linear Optimal Transport in spatial transcriptome reconstruction LLOT：拉普拉斯线性优化传输在空间转录组重建中的应用

arXiv - STAT - Applications Pub Date : 2024-08-27 DOI: arxiv-2408.15149

Junhao Zhu, Kevin Zhang, Dehan Kong, Zhaolei Zhang

{"title":"LLOT: application of Laplacian Linear Optimal Transport in spatial transcriptome reconstruction","authors":"Junhao Zhu, Kevin Zhang, Dehan Kong, Zhaolei Zhang","doi":"arxiv-2408.15149","DOIUrl":"https://doi.org/arxiv-2408.15149","url":null,"abstract":"Single-cell RNA sequencing (scRNA-seq) allows transcriptional profiling, and\u0000cell-type annotation of individual cells. However, sample preparation in\u0000typical scRNA-seq experiments often homogenizes the samples, thus spatial\u0000locations of individual cells are often lost. Although spatial transcriptomic\u0000techniques, such as in situ hybridization (ISH) or Slide-seq, can be used to\u0000measure gene expression in specific locations in samples, it remains a\u0000challenge to measure or infer expression level for every gene at a single-cell\u0000resolution in every location in tissues. Existing computational methods show\u0000promise in reconstructing these missing data by integrating scRNA-seq data with\u0000spatial expression data such as those obtained from spatial transcriptomics.\u0000Here we describe Laplacian Linear Optimal Transport (LLOT), an interpretable\u0000method to integrate single-cell and spatial transcriptomics data to reconstruct\u0000missing information at a whole-genome and single-cell resolution. LLOT\u0000iteratively corrects platform effects and employs Laplacian Optimal Transport\u0000to decompose each spot in spatial transcriptomics data into a spatially-smooth\u0000probabilistic mixture of single cells. We benchmarked LLOT against several\u0000other methods on datasets of Drosophila embryo, mouse cerebellum and synthetic\u0000datasets generated by scDesign3 in the paper, and another three datasets in the\u0000supplementary. The results showed that LLOT consistently outperformed others in\u0000reconstructing spatial expressions.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"68 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Bayesian spatiotemporal modelling of political violence and conflict events using discrete-time Hawkes processes 利用离散时间霍克斯过程对政治暴力和冲突事件进行贝叶斯时空建模

arXiv - STAT - Applications Pub Date : 2024-08-27 DOI: arxiv-2408.14940

Raiha Browning, Hamish Patten, Judith Rousseau, Kerrie Mengersen

{"title":"Bayesian spatiotemporal modelling of political violence and conflict events using discrete-time Hawkes processes","authors":"Raiha Browning, Hamish Patten, Judith Rousseau, Kerrie Mengersen","doi":"arxiv-2408.14940","DOIUrl":"https://doi.org/arxiv-2408.14940","url":null,"abstract":"Monitoring of conflict risk in the humanitarian sector is largely based on\u0000simple historic averages. To advance our understanding, we propose Hawkes\u0000processes, a self-exciting stochastic process used to describe phenomena\u0000whereby past events increase the probability of future events occurring. The\u0000overarching goal of this work is to assess the potential for using a more\u0000statistically rigorous approach to monitor the risk of political violence and\u0000conflict events in practice and characterise their temporal and spatial\u0000patterns. The region of South Asia was selected as an exemplar of how our model can be\u0000applied globally. We individually analyse the various types of conflict events\u0000for the countries in this region and compare the results. A Bayesian,\u0000spatiotemporal variant of the Hawkes process is fitted to data gathered by the\u0000Armed Conflict Location and Event Data (ACLED) project to obtain sub-national\u0000estimates of conflict risk over time and space. Our model can effectively\u0000estimate the risk level of these events within a statistically sound framework,\u0000with a more precise understanding of the uncertainty around these estimates\u0000than was previously possible. This work enables a better understanding of\u0000conflict events which can inform preventative measures. We demonstrate the advantages of the Bayesian framework by comparing our\u0000results to maximum likelihood estimation. While maximum likelihood gives\u0000reasonable point estimates, the Bayesian approach is preferred when possible.\u0000Practical examples are presented to demonstrate how the proposed model can be\u0000used to monitor conflict risk. Comparing to current practices that rely on\u0000historical averages, we also show that our model is more stable and robust to\u0000outliers. In this work we aim to support actors in the humanitarian sector in\u0000making data-informed decisions, such as the allocation of resources in\u0000conflict-prone regions.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142224456","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluating the effectiveness of public policies on COVID-19 containment: A PSM-DID approach 评估遏制 COVID-19 的公共政策的有效性：PSM-DID 方法

arXiv - STAT - Applications Pub Date : 2024-08-26 DOI: arxiv-2408.14108

Zihan Wang

引用次数: 0

Bayesian functional data analysis in astronomy 天文学中的贝叶斯函数数据分析

arXiv - STAT - Applications Pub Date : 2024-08-26 DOI: arxiv-2408.14466

Thomas Loredo, Tamas Budavari, David Kent, David Ruppert

{"title":"Bayesian functional data analysis in astronomy","authors":"Thomas Loredo, Tamas Budavari, David Kent, David Ruppert","doi":"arxiv-2408.14466","DOIUrl":"https://doi.org/arxiv-2408.14466","url":null,"abstract":"Cosmic demographics -- the statistical study of populations of astrophysical\u0000objects -- has long relied on *multivariate statistics*, providing methods for\u0000analyzing data comprising fixed-length vectors of properties of objects, as\u0000might be compiled in a tabular astronomical catalog (say, with sky coordinates,\u0000and brightness measurements in a fixed number of spectral passbands). But\u0000beginning with the emergence of automated digital sky surveys, ca. ~2000,\u0000astronomers began producing large collections of data with more complex\u0000structure: light curves (brightness time series) and spectra (brightness vs.\u0000wavelength). These comprise what statisticians call *functional data* --\u0000measurements of populations of functions. Upcoming automated sky surveys will\u0000soon provide astronomers with a flood of functional data. New methods are\u0000needed to accurately and optimally analyze large ensembles of light curves and\u0000spectra, accumulating information both along and across measured functions.\u0000Functional data analysis (FDA) provides tools for statistical modeling of\u0000functional data. Astronomical data presents several challenges for FDA\u0000methodology, e.g., sparse, irregular, and asynchronous sampling, and\u0000heteroscedastic measurement error. Bayesian FDA uses hierarchical Bayesian\u0000models for function populations, and is well suited to addressing these\u0000challenges. We provide an overview of astronomical functional data, and of some\u0000key Bayesian FDA modeling approaches, including functional mixed effects\u0000models, and stochastic process models. We briefly describe a Bayesian FDA\u0000framework combining FDA and machine learning methods to build low-dimensional\u0000parametric models for galaxy spectra.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimation of time-varying recovery and death rates from epidemiological data: A new approach 从流行病学数据中估算随时间变化的康复率和死亡率：一种新方法

arXiv - STAT - Applications Pub Date : 2024-08-25 DOI: arxiv-2408.13872

Samiran Ghosh, Malay Banerjee, Subhra Sankar Dhar, Siuli Mukhopadhyay

{"title":"Estimation of time-varying recovery and death rates from epidemiological data: A new approach","authors":"Samiran Ghosh, Malay Banerjee, Subhra Sankar Dhar, Siuli Mukhopadhyay","doi":"arxiv-2408.13872","DOIUrl":"https://doi.org/arxiv-2408.13872","url":null,"abstract":"The time-to-recovery or time-to-death for various infectious diseases can\u0000vary significantly among individuals, influenced by several factors such as\u0000demographic differences, immune strength, medical history, age, pre-existing\u0000conditions, and infection severity. To capture these variations,\u0000time-since-infection dependent recovery and death rates offer a detailed\u0000description of the epidemic. However, obtaining individual-level data to\u0000estimate these rates is challenging, while aggregate epidemiological data (such\u0000as the number of new infections, number of active cases, number of new\u0000recoveries, and number of new deaths) are more readily available. In this\u0000article, a new methodology is proposed to estimate time-since-infection\u0000dependent recovery and death rates using easily available data sources,\u0000accommodating irregular data collection timings reflective of real-world\u0000reporting practices. The Nadaraya-Watson estimator is utilized to derive the\u0000number of new infections. This model improves the accuracy of epidemic\u0000progression descriptions and provides clear insights into recovery and death\u0000distributions. The proposed methodology is validated using COVID-19 data and\u0000its general applicability is demonstrated by applying it to some other diseases\u0000like measles and typhoid.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187912","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Examining Differential Item Functioning (DIF) in Self-Reported Health Survey Data: Via Multilevel Modeling 检验自我健康调查数据中的差异项目功能 (DIF)：通过多层次建模

arXiv - STAT - Applications Pub Date : 2024-08-25 DOI: arxiv-2408.13702

Dandan Chen Kaptur, Yiqing Liu, Bradley Kaptur, Nicholas Peterman, Jinming Zhang, Justin Kern, Carolyn Anderson

{"title":"Examining Differential Item Functioning (DIF) in Self-Reported Health Survey Data: Via Multilevel Modeling","authors":"Dandan Chen Kaptur, Yiqing Liu, Bradley Kaptur, Nicholas Peterman, Jinming Zhang, Justin Kern, Carolyn Anderson","doi":"arxiv-2408.13702","DOIUrl":"https://doi.org/arxiv-2408.13702","url":null,"abstract":"Few health-related constructs or measures have received critical evaluation\u0000in terms of measurement equivalence, such as self-reported health survey data.\u0000Differential item functioning (DIF) analysis is crucial for evaluating\u0000measurement equivalence in self-reported health surveys, which are often\u0000hierarchical in structure. While traditional DIF methods rely on single-level\u0000models, multilevel models offer a more suitable alternative for analyzing such\u0000data. In this article, we highlight the advantages of multilevel modeling in\u0000DIF analysis and demonstrate how to apply the DIF framework to self-reported\u0000health survey data using multilevel models. For demonstration, we analyze DIF\u0000associated with population density on the probability to answer \"Yes\" to a\u0000survey question on depression and reveal that multilevel models achieve better\u0000fit and account for more variance compared to single-level models. This article\u0000is expected to increase awareness of the usefulness of multilevel modeling for\u0000DIF analysis and assist healthcare researchers and practitioners in improving\u0000the understanding of self-reported health survey data validity.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142187913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0