This paper introduces the usage and performance of the R package tlrmvnmvt, aimed at computing high-dimensional multivariate normal and Student-t probabilities. The package implements the tile-low-rank methods with block reordering and the separationof-variable methods with univariate reordering. The performance is compared with two other state-of-the-art R packages, namely the mvtnorm and the TruncatedNormal packages. Our package has the best scalability and is likely to be the only option in thousands of dimensions. However, for applications with high accuracy requirements, the TruncatedNormal package is more suitable. As an application example, we show that the excursion sets of a latent Gaussian random field can be computed with the tlrmvnmvt package without any model approximation and hence, the accuracy of the produced excursion sets is improved.
{"title":"tlrmvnmvt: Computing High-Dimensional Multivariate Normal and Student- t Probabilities with Low-Rank Methods in R","authors":"Jian Cao, M. Genton, D. Keyes, G. Turkiyyah","doi":"10.18637/jss.v101.i04","DOIUrl":"https://doi.org/10.18637/jss.v101.i04","url":null,"abstract":"This paper introduces the usage and performance of the R package tlrmvnmvt, aimed at computing high-dimensional multivariate normal and Student-t probabilities. The package implements the tile-low-rank methods with block reordering and the separationof-variable methods with univariate reordering. The performance is compared with two other state-of-the-art R packages, namely the mvtnorm and the TruncatedNormal packages. Our package has the best scalability and is likely to be the only option in thousands of dimensions. However, for applications with high accuracy requirements, the TruncatedNormal package is more suitable. As an application example, we show that the excursion sets of a latent Gaussian random field can be computed with the tlrmvnmvt package without any model approximation and hence, the accuracy of the produced excursion sets is improved.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76051787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Pro Data Visualization Using R and JavaScript: Analyze and Visualize Key Data on the Web","authors":"U. Grömping","doi":"10.18637/jss.v102.b01","DOIUrl":"https://doi.org/10.18637/jss.v102.b01","url":null,"abstract":"","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87480454","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computation in many fields including those that use statistical software is increasingly driven by needs that can be addressed in many programming ecosystems. In projects that require statistical analyses, both R and Python comprise two frequent resources. In ecology, R is the most frequently used (Lai, Lortie, Muenchen, Yang, and Ma 2019). In bioinformatic gene set analyses, R is also more frequently used in peer-reviewed publications, but Python is still an important statistical resource depending on the specific project (Xie, Jauhari, and Mora 2021). Python outcompetes other languages in use for machine learning and some forms of factor analyses (Hao and Ho 2019; Persson and Khojasteh 2021; Raschka, Patterson, and Nolet 2020). However, the relative frequency that a tool is used for statistical analyses is only one metric of importance and not necessarily a proxy for its merit or its capacity to support innovation and efficient in analyses for practitioners (Zhao, Yan, and Li 2018). It is thus critical that we explore contrasts of at least these two common software languages that support statistics because data scientists can become isolated or polarized within their specific competencies, ideologies, and workflows. A high-level discussion of strengths and weaknesses specific to data endeavors with statistics is germane to both decisions on specific projects and on competency development as a scientist.
包括使用统计软件在内的许多领域的计算越来越多地受到许多编程生态系统中可以解决的需求的驱动。在需要统计分析的项目中，R和Python都包含两种常用资源。在生态学中，R是最常用的(Lai, Lortie, Muenchen, Yang, and Ma 2019)。在生物信息学基因集分析中，R也更频繁地用于同行评审的出版物，但根据具体项目，Python仍然是重要的统计资源(Xie, Jauhari, and Mora 2021)。Python在机器学习和某些形式的因素分析方面胜过其他语言(Hao and Ho 2019;Persson and Khojasteh 2021;Raschka, Patterson, and Nolet 2020)。然而，工具用于统计分析的相对频率只是一个重要的度量标准，并不一定代表其优点或支持从业者创新和高效分析的能力(Zhao, Yan, and Li, 2018)。因此，我们探索至少这两种支持统计的常见软件语言的对比是至关重要的，因为数据科学家可能在他们的特定能力、意识形态和工作流程中变得孤立或两极分化。对统计数据的优缺点进行高层次的讨论，对具体项目的决策和作为科学家的能力发展都是有密切关系的。
{"title":"Python and R for the Modern Data Scientist","authors":"C. Lortie","doi":"10.18637/jss.v103.b02","DOIUrl":"https://doi.org/10.18637/jss.v103.b02","url":null,"abstract":"Computation in many fields including those that use statistical software is increasingly driven by needs that can be addressed in many programming ecosystems. In projects that require statistical analyses, both R and Python comprise two frequent resources. In ecology, R is the most frequently used (Lai, Lortie, Muenchen, Yang, and Ma 2019). In bioinformatic gene set analyses, R is also more frequently used in peer-reviewed publications, but Python is still an important statistical resource depending on the specific project (Xie, Jauhari, and Mora 2021). Python outcompetes other languages in use for machine learning and some forms of factor analyses (Hao and Ho 2019; Persson and Khojasteh 2021; Raschka, Patterson, and Nolet 2020). However, the relative frequency that a tool is used for statistical analyses is only one metric of importance and not necessarily a proxy for its merit or its capacity to support innovation and efficient in analyses for practitioners (Zhao, Yan, and Li 2018). It is thus critical that we explore contrasts of at least these two common software languages that support statistics because data scientists can become isolated or polarized within their specific competencies, ideologies, and workflows. A high-level discussion of strengths and weaknesses specific to data endeavors with statistics is germane to both decisions on specific projects and on competency development as a scientist.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72785050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper describes the gretl function package ParMA , which provides Bayesian model averaging (BMA) in generalized linear models. In order to overcome the lack of analytical specification for many of the models covered, the package features an implementation of the reversible jump Markov chain Monte Carlo technique, following the original idea by Green (1995), as a flexible tool to model several specifications. Particular attention is devoted to computational aspects such as the automatization of the model building procedure and the parallelization of the sampling scheme.
{"title":"ParMA: Parallelized Bayesian Model Averaging for Generalized Linear Models","authors":"R. Lucchetti, Luca Pedini","doi":"10.18637/jss.v104.i02","DOIUrl":"https://doi.org/10.18637/jss.v104.i02","url":null,"abstract":"This paper describes the gretl function package ParMA , which provides Bayesian model averaging (BMA) in generalized linear models. In order to overcome the lack of analytical specification for many of the models covered, the package features an implementation of the reversible jump Markov chain Monte Carlo technique, following the original idea by Green (1995), as a flexible tool to model several specifications. Particular attention is devoted to computational aspects such as the automatization of the model building procedure and the parallelization of the sampling scheme.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87323845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
synthACS is an R package that provides flexible tools for building synthetic micro-datasets based on American Community Survey (ACS) base tables, allows data-extensibility and enables to conduct spatial microsimulation modeling (SMSM) via simulated annealing. To our knowledge, it is the first R package to provide broadly applicable tools for SMSM with ACS data as well as the first SMSM implementation that uses unequal probability sampling in the simulated annealing algorithm. In this paper, we contextualize these developments within the SMSM literature, provide a hands-on user-guide to package synthACS , present a case study of SMSM related to population dynamics, and note areas for future research.
{"title":"synthACS: Spatial Microsimulation Modeling with Synthetic American Community Survey Data","authors":"Alex P. Whitworth","doi":"10.18637/jss.v104.i07","DOIUrl":"https://doi.org/10.18637/jss.v104.i07","url":null,"abstract":"synthACS is an R package that provides flexible tools for building synthetic micro-datasets based on American Community Survey (ACS) base tables, allows data-extensibility and enables to conduct spatial microsimulation modeling (SMSM) via simulated annealing. To our knowledge, it is the first R package to provide broadly applicable tools for SMSM with ACS data as well as the first SMSM implementation that uses unequal probability sampling in the simulated annealing algorithm. In this paper, we contextualize these developments within the SMSM literature, provide a hands-on user-guide to package synthACS , present a case study of SMSM related to population dynamics, and note areas for future research.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76993187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"[RETRACTED ARTICLE] irtplay: An R Package for Unidimensional Item Response Theory Modeling","authors":"Hwanggyu Lim, C. Wells","doi":"10.18637/jss.v103.i12","DOIUrl":"https://doi.org/10.18637/jss.v103.i12","url":null,"abstract":"","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75684716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Scientific synthesis is a diverse field of contemporary science. Syntheses advance knowledge in many domains and can include data compilation, theory syntheses, methods contrasts, and systematic reviews with meta-analyses through an integrated and big-picture view of evidence (Halpern et al. 2020). All these knowledge tools are typically strongly supported by statistical software including the open-source programming language R. Within this environment, there are nearly 100 packages to support meta-analyses each with different functions and specific capabilities (Lortie and Filazzola 2020). Meta-analyses are defined in most domains as the calculation of effect sizes or a weighted relative strength of evidence from a set of studies or trials to then subsequently examine high-level statistical patterns and variance (Gurevitch, Koricheva, Nakagawa, and Stewart 2018). They are increasingly used in many fields of science to examine consilience in hypotheses (Lortie 2014) and have been proposed as the gold or even platinum standard of evidence when there is statistical agreement in the efficacy of an intervention across studies (Stegenga 2011). Consequently, there is a critical need for accessible, pragmatic publications, resources, and texts that enable scientists with varying levels of expertise to engage in scientific syntheses using meta-analysis.
科学综合是当代科学的一个多元化领域。综合促进了许多领域的知识，可以包括数据汇编、理论综合、方法对比，以及通过综合和大视角的证据进行meta分析的系统综述(Halpern et al. 2020)。所有这些知识工具通常都得到统计软件的大力支持，包括开源编程语言r。在这个环境中，有近100个软件包支持元分析，每个软件包具有不同的功能和特定功能(Lortie和Filazzola 2020)。在大多数领域，荟萃分析被定义为计算效应大小或来自一组研究或试验的加权证据的相对强度，然后检查高级统计模式和方差(Gurevitch, Koricheva, Nakagawa, and Stewart 2018)。它们越来越多地用于许多科学领域，以检查假设的一致性(Lortie 2014)，并且当在研究中干预的有效性存在统计一致性时，已被提议作为金甚至白金证据标准(Stegenga 2011)。因此，迫切需要可访问的、实用的出版物、资源和文本，使具有不同专业水平的科学家能够使用元分析进行科学综合。
{"title":"Doing Meta-Analysis with R - A Hands-On Guide","authors":"C. Lortie","doi":"10.18637/jss.v102.b02","DOIUrl":"https://doi.org/10.18637/jss.v102.b02","url":null,"abstract":"Scientific synthesis is a diverse field of contemporary science. Syntheses advance knowledge in many domains and can include data compilation, theory syntheses, methods contrasts, and systematic reviews with meta-analyses through an integrated and big-picture view of evidence (Halpern et al. 2020). All these knowledge tools are typically strongly supported by statistical software including the open-source programming language R. Within this environment, there are nearly 100 packages to support meta-analyses each with different functions and specific capabilities (Lortie and Filazzola 2020). Meta-analyses are defined in most domains as the calculation of effect sizes or a weighted relative strength of evidence from a set of studies or trials to then subsequently examine high-level statistical patterns and variance (Gurevitch, Koricheva, Nakagawa, and Stewart 2018). They are increasingly used in many fields of science to examine consilience in hypotheses (Lortie 2014) and have been proposed as the gold or even platinum standard of evidence when there is statistical agreement in the efficacy of an intervention across studies (Stegenga 2011). Consequently, there is a critical need for accessible, pragmatic publications, resources, and texts that enable scientists with varying levels of expertise to engage in scientific syntheses using meta-analysis.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77664859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper presents the R package plot3logit which enables the covariate effects of trinomial regression models to be represented graphically by means of a ternary plot. The aim of the plot is helping the interpretation of regression coefficients in terms of the effects that a change in values of regressors has on the probability distribution of the dependent variable. Such changes may involve either a single regressor, or a group of them (composite changes), and the package permits both cases to be handled in a user-friendly way. Moreover, plot3logit can compute and draw confidence regions of the effects of covariate changes and enables multiple changes and profiles to be represented and compared jointly. Upstream and downstream compatibility makes the package able to work with other R packages or applications other than R .
{"title":"plot3logit: Ternary Plots for Interpreting Trinomial Regression Models","authors":"F. Santi, M. M. Dickson, G. Espa, D. Giuliani","doi":"10.18637/jss.v103.c01","DOIUrl":"https://doi.org/10.18637/jss.v103.c01","url":null,"abstract":"This paper presents the R package plot3logit which enables the covariate effects of trinomial regression models to be represented graphically by means of a ternary plot. The aim of the plot is helping the interpretation of regression coefficients in terms of the effects that a change in values of regressors has on the probability distribution of the dependent variable. Such changes may involve either a single regressor, or a group of them (composite changes), and the package permits both cases to be handled in a user-friendly way. Moreover, plot3logit can compute and draw confidence regions of the effects of covariate changes and enables multiple changes and profiles to be represented and compared jointly. Upstream and downstream compatibility makes the package able to work with other R packages or applications other than R .","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82501290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
UComp is a powerful library for building unobserved components models, useful for forecasting and other important operations, such us de-trending, cycle analysis, seasonal adjustment, signal extraction, etc. One of the most outstanding features that makes UComp unique among its class of related software implementations is that models may be built automatically by identification algorithms (three versions are available). These algorithms select the best model among many possible combinations. Another relevant feature is that it is coded in C++ , opening the door to link it to different popular and widely used environments, like R , MATLAB , Octave , Python , etc. The implemented models for the components are more general than the usual ones in the field of unobserved components modeling, including different types of trend, cycle, seasonal and irregular components, input variables and outlier detection. The automatic character of the algorithms required the development of many complementary algorithms to control performance and make it applicable to as many different time series as possible. The library is open source and available in different formats in public repositories. The performance of the library is illustrated working on real data in several varied examples.
{"title":"Automatic Identification and Forecasting of Structural Unobserved Components Models with UComp","authors":"D. J. Pedregal","doi":"10.18637/jss.v103.i09","DOIUrl":"https://doi.org/10.18637/jss.v103.i09","url":null,"abstract":"UComp is a powerful library for building unobserved components models, useful for forecasting and other important operations, such us de-trending, cycle analysis, seasonal adjustment, signal extraction, etc. One of the most outstanding features that makes UComp unique among its class of related software implementations is that models may be built automatically by identification algorithms (three versions are available). These algorithms select the best model among many possible combinations. Another relevant feature is that it is coded in C++ , opening the door to link it to different popular and widely used environments, like R , MATLAB , Octave , Python , etc. The implemented models for the components are more general than the usual ones in the field of unobserved components modeling, including different types of trend, cycle, seasonal and irregular components, input variables and outlier detection. The automatic character of the algorithms required the development of many complementary algorithms to control performance and make it applicable to as many different time series as possible. The library is open source and available in different formats in public repositories. The performance of the library is illustrated working on real data in several varied examples.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88563192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Carel F. W. Peeters, A. E. Bilgrau, W. V. van Wieringen
{"title":"rags2ridges: A One-Stop- ℓ2 -Shop for ","authors":"Carel F. W. Peeters, A. E. Bilgrau, W. V. van Wieringen","doi":"10.18637/jss.v102.i04","DOIUrl":"https://doi.org/10.18637/jss.v102.i04","url":null,"abstract":"","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":null,"pages":null},"PeriodicalIF":5.8,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"67679193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：