arXiv - STAT - Applications最新文献_第10页

Analysis of the Impact of Unforced Errors in Tennis 网球非强迫性失误的影响分析

arXiv - STAT - Applications Pub Date : 2024-07-27 DOI: arxiv-2407.19321

Hashan Peiris, Nirodha Epasinghege Dona, Tim Swartz

引用次数: 0

A Versatility Measure for Parametric Risk Models 参数风险模型的通用度量方法

arXiv - STAT - Applications Pub Date : 2024-07-27 DOI: arxiv-2407.19218

Michael R. Powers, Jiaxin Xu

引用次数: 0

A Public Dataset For the ZKsync Rollup 用于 ZKsync 滚动的公共数据集

arXiv - STAT - Applications Pub Date : 2024-07-26 DOI: arxiv-2407.18699

Maria Inês Silva, Johnnatan Messias, Benjamin Livshits

引用次数: 0

Regularized Adjusted Plus-Minus Models for Evaluating and Scouting Football (Soccer) Players using Possession Sequences 利用控球序列评估和侦察足球（橄榄球）运动员的正规化调整正负值模型

arXiv - STAT - Applications Pub Date : 2024-07-25 DOI: arxiv-2407.17832

Robert Bajons, Kurt Hornik

{"title":"Regularized Adjusted Plus-Minus Models for Evaluating and Scouting Football (Soccer) Players using Possession Sequences","authors":"Robert Bajons, Kurt Hornik","doi":"arxiv-2407.17832","DOIUrl":"https://doi.org/arxiv-2407.17832","url":null,"abstract":"This paper presents a novel framework for evaluating players in association\u0000football (soccer). Our method uses possession sequences, i.e. sequences of\u0000consecutive on-ball actions, for deriving estimates for player strengths. On\u0000the surface, the methodology is similar to classical adjusted plus-minus rating\u0000models using mainly regularized regression techniques. However, by analyzing\u0000possessions, our framework is able to distinguish on-ball and off-ball\u0000contributions of players to the game. From a methodological viewpoint, the\u0000framework explores four different penalization schemes, which exploit\u0000football-specific structures such as the grouping of players into position\u0000groups as well as into common strength groups. These four models lead to four\u0000ways to rate players by considering the respective estimate of each model\u0000corresponding to the player. The ratings are used to analyze the 2017/18 season\u0000of the Spanish La Liga. We compare similarities as well as particular use cases\u0000of each of the penalized models and provide guidance for practitioners when\u0000using the individual model specifications. Finally, we conclude our analysis by\u0000providing a domain-specific statistical evaluation framework, which highlights\u0000the potential of the penalized regression approaches for evaluating players.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141780176","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 Nowcasting Data Breach IBNR Incidents 贝叶斯预测数据泄露 IBNR 事件

arXiv - STAT - Applications Pub Date : 2024-07-25 DOI: arxiv-2407.18377

Maochao Xu, Hong Sun, Peng Zhao

引用次数: 0

Comparison of global sensitivity analysis methods for a fire spread model with a segmented characteristic 具有分段特征的火灾蔓延模型的全局敏感性分析方法比较

arXiv - STAT - Applications Pub Date : 2024-07-25 DOI: arxiv-2407.17718

Shi-Shun Chen, Xiao-Yang Li

引用次数: 0

Organizational Effectiveness: A New Strategy to Leverage Multisite Randomized Trials for Valid Assessment 组织效能：利用多地点随机试验进行有效评估的新策略

arXiv - STAT - Applications Pub Date : 2024-07-25 DOI: arxiv-2407.18360

Guanglei HongUniversity of Chicago, Jonah DeutschMathematica, Peter KressMathematica, Jose Eos TrinidadUniversity of California-Berkeley, Zhengyan XuUniversity of Pennsylvania

{"title":"Organizational Effectiveness: A New Strategy to Leverage Multisite Randomized Trials for Valid Assessment","authors":"Guanglei HongUniversity of Chicago, Jonah DeutschMathematica, Peter KressMathematica, Jose Eos TrinidadUniversity of California-Berkeley, Zhengyan XuUniversity of Pennsylvania","doi":"arxiv-2407.18360","DOIUrl":"https://doi.org/arxiv-2407.18360","url":null,"abstract":"In education, health, and human services, an intervention program is usually\u0000implemented by many local organizations. Determining which organizations are\u0000more effective is essential for theoretically characterizing effective\u0000practices and for intervening to enhance the capacity of ineffective\u0000organizations. In multisite randomized trials, site-specific intention-to-treat\u0000(ITT) effects are likely invalid indicators for organizational effectiveness\u0000and may lead to inequitable decisions. This is because sites differ in their\u0000local ecological conditions including client composition, alternative programs,\u0000and community context. Applying the potential outcomes framework, this study\u0000proposes a mathematical definition for the relative effectiveness of an\u0000organization. The estimand contrasts the performance of a focal organization\u0000with those that share the features of its local ecological conditions. The\u0000identification relies on relatively weak assumptions by leveraging observed\u0000control group outcomes that capture the confounding impacts of alternative\u0000programs and community context. We propose a two-step mixed-effects modeling\u0000(2SME) procedure. Simulations demonstrate significant improvements when\u0000compared with site-specific ITT analyses or analyses that only adjust for\u0000between-site differences in the observed baseline participant composition. We\u0000illustrate its use through an evaluation of the relative effectiveness of\u0000individual Job Corps centers by reanalyzing data from the National Job Corps\u0000Study, a multisite randomized trial that included 100 Job Corps centers\u0000nationwide serving disadvantaged youths. The new strategy promises to alleviate\u0000consequential misclassifications of some of the most effective Job Corps\u0000centers as least effective and vice versa.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141866539","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

Integrating Ensemble Kalman Filter with AI-based Weather Prediction Model ClimaX 将集合卡尔曼滤波器与人工智能天气预报模型 ClimaX 相结合

arXiv - STAT - Applications Pub Date : 2024-07-25 DOI: arxiv-2407.17781

Shunji Kotsuki, Kenta Shiraishi, Atsushi Okazaki

{"title":"Integrating Ensemble Kalman Filter with AI-based Weather Prediction Model ClimaX","authors":"Shunji Kotsuki, Kenta Shiraishi, Atsushi Okazaki","doi":"arxiv-2407.17781","DOIUrl":"https://doi.org/arxiv-2407.17781","url":null,"abstract":"Artificial intelligence (AI)-based weather prediction research is growing\u0000rapidly and has shown to be competitive with the advanced dynamic numerical\u0000weather prediction models. However, research combining AI-based weather\u0000prediction models with data assimilation remains limited partially because\u0000long-term sequential data assimilation cycles are required to evaluate data\u0000assimilation systems. This study explores integrating the local ensemble\u0000transform Kalman filter (LETKF) with an AI-based weather prediction model\u0000ClimaX. Our experiments demonstrated that the ensemble data assimilation cycled\u0000stably for the AI-based weather prediction model using covariance inflation and\u0000localization techniques inside the LETKF. While ClimaX showed some limitations\u0000in capturing flow-dependent error covariance compared to dynamical models, the\u0000AI-based ensemble forecasts provided reasonable and beneficial error covariance\u0000in sparsely observed regions. These findings highlight the potential of AI\u0000models in weather forecasting and the importance of physical consistency and\u0000accurate error growth representation in improving ensemble data assimilation.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141780179","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

A new moment-independent uncertainty importance measure based on cumulative residual entropy for developing uncertainty reduction strategies 基于累积残差熵的新的与时刻无关的不确定性重要性度量，用于制定减少不确定性的策略

arXiv - STAT - Applications Pub Date : 2024-07-25 DOI: arxiv-2407.17719

Shi-Shun Chen, Xiao-Yang Li

{"title":"A new moment-independent uncertainty importance measure based on cumulative residual entropy for developing uncertainty reduction strategies","authors":"Shi-Shun Chen, Xiao-Yang Li","doi":"arxiv-2407.17719","DOIUrl":"https://doi.org/arxiv-2407.17719","url":null,"abstract":"Uncertainty reduction is vital for improving system reliability and reducing\u0000risks. To identify the best target for uncertainty reduction, uncertainty\u0000importance measure is commonly used to prioritize the significance of input\u0000variable uncertainties. Then, designers will take steps to reduce the\u0000uncertainties of variables with high importance. However, for variables with\u0000minimal uncertainty, the cost of controlling their uncertainties can be\u0000unacceptable. Therefore, uncertainty magnitude should also be considered in\u0000developing uncertainty reduction strategies. Although variance-based methods\u0000have been developed for this purpose, they are dependent on statistical moments\u0000and have limitations when dealing with highly-skewed distributions that are\u0000commonly encountered in practical applications. Motivated by this problem, we\u0000propose a new uncertainty importance measure based on cumulative residual\u0000entropy. The proposed measure is moment-independent based on the cumulative\u0000distribution function, which can handle the highly-skewed distributions\u0000properly. Numerical implementations for estimating the proposed measure are\u0000devised and verified. A real-world engineering case considering highly-skewed\u0000distributions is introduced to show the procedure of developing uncertainty\u0000reduction strategies considering uncertainty magnitude and corresponding cost.\u0000The results demonstrate that the proposed measure can present a different\u0000uncertainty reduction recommendation compared to the variance-based approach\u0000because of its moment-independent characteristic.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141780177","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

Longitudinal Principal Manifold Estimation 纵向主模型估算

arXiv - STAT - Applications Pub Date : 2024-07-24 DOI: arxiv-2407.17450

Robert Zielinski, Kun Meng, Ani Eloyan

{"title":"Longitudinal Principal Manifold Estimation","authors":"Robert Zielinski, Kun Meng, Ani Eloyan","doi":"arxiv-2407.17450","DOIUrl":"https://doi.org/arxiv-2407.17450","url":null,"abstract":"Longitudinal magnetic resonance imaging data is used to model trajectories of\u0000change in brain regions of interest to identify areas susceptible to atrophy in\u0000those with neurodegenerative conditions like Alzheimer's disease. Most methods\u0000for extracting brain regions are applied to scans from study participants\u0000independently, resulting in wide variability in shape and volume estimates of\u0000these regions over time in longitudinal studies. To address this problem, we\u0000propose a longitudinal principal manifold estimation method, which seeks to\u0000recover smooth, longitudinally meaningful manifold estimates of shapes over\u0000time. The proposed approach uses a smoothing spline to smooth over the\u0000coefficients of principal manifold embedding functions estimated at each time\u0000point. This mitigates the effects of random disturbances to the manifold\u0000between time points. Additionally, we propose a novel data augmentation\u0000approach to enable principal manifold estimation on self-intersecting\u0000manifolds. Simulation studies demonstrate performance improvements over naive\u0000applications of principal manifold estimation and principal curve/surface\u0000methods. The proposed method improves the estimation of surfaces of\u0000hippocampuses and thalamuses using data from participants of the Alzheimer's\u0000Disease Neuroimaging Initiative. An analysis of magnetic resonance imaging data\u0000from 236 individuals shows the advantages of our proposed methods that leverage\u0000regional longitudinal trends for segmentation.","PeriodicalId":501172,"journal":{"name":"arXiv - STAT - Applications","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141780180","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