In this summary we introduce the papers published in the special issue on Bayesian statistics. This special issue comprises 20 papers on Bayesian statistics and Bayesian inference on different topics such as general packages for hierarchical linear model fitting, survival models, clinical trials, missing values, time series, hypothesis testing, priors, approximate Bayesian computation, and others.
{"title":"Software for Bayesian Statistics","authors":"M. Cameletti, V. Gómez‐Rubio","doi":"10.18637/jss.v100.i01","DOIUrl":"https://doi.org/10.18637/jss.v100.i01","url":null,"abstract":"In this summary we introduce the papers published in the special issue on Bayesian statistics. This special issue comprises 20 papers on Bayesian statistics and Bayesian inference on different topics such as general packages for hierarchical linear model fitting, survival models, clinical trials, missing values, time series, hypothesis testing, priors, approximate Bayesian computation, and others.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"482 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90921509","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}
Pub Date : 2021-01-01Epub Date: 2021-11-30DOI: 10.18637/jss.v100.i21
Barry S Eggleston, Joseph G Ibrahim, Becky McNeil, Diane Catellier
This article introduces the R (R Core Team 2019) package BayesCTDesign for two-arm randomized Bayesian trial design using historical control data when available, and simple two-arm randomized Bayesian trial design when historical control data is not available. The package BayesCTDesign, which is available on CRAN, has two simulation functions, historic_sim() and simple_sim() for studying trial characteristics under user defined scenarios, and two methods print() and plot() for displaying summaries of the simulated trial characteristics. The package BayesCTDesign works with two-arm trials with equal sample sizes per arm. The package BayesCTDesign allows a user to study Gaussian, Poisson, Bernoulli, Weibull, Lognormal, and Piecewise Exponential (pwe) outcomes. Power for two-sided hypothesis tests at a user defined alpha is estimated via simulation using a test within each simulation replication that involves comparing a 95% credible interval for the outcome specific treatment effect measure to the null case value. If the 95% credible interval excludes the null case value, then the null hypothesis is rejected, else the null hypothesis is accepted. In the article, the idea of including historical control data in a Bayesian analysis is reviewed, the estimation process of BayesCTDesign is explained, and the user interface is described. Finally, the BayesCTDesign is illustrated via several examples.
本文介绍了R（R Core Team 2019）软件包BayesCTDesign，用于在可用的情况下使用历史对照数据进行双臂随机贝叶斯试验设计，以及在没有历史对照数据时进行简单的双臂随机贝叶斯试验设计。CRAN上提供的包BayesCTDesign有两个模拟函数，historic_sim（）和simple_sim（。BayesCTDesign软件包适用于两个手臂试验，每个手臂的样本量相等。包BayesCTDesign允许用户研究高斯、泊松、伯努利、威布尔、对数正态和逐段指数（pwe）结果。通过在每个模拟复制中使用测试的模拟来估计用户定义的α下的双侧假设测试的功率，该测试涉及将结果特异性治疗效果测量的95%可信区间与零病例值进行比较。如果95%可信区间排除了零情况值，则拒绝零假设，否则接受零假设。本文回顾了将历史控制数据纳入贝叶斯分析的思想，解释了贝叶斯设计的估计过程，并描述了用户界面。最后，通过几个例子说明了贝叶斯TDesign。
{"title":"BayesCTDesign: An R Package for Bayesian Trial Design Using Historical Control Data.","authors":"Barry S Eggleston, Joseph G Ibrahim, Becky McNeil, Diane Catellier","doi":"10.18637/jss.v100.i21","DOIUrl":"10.18637/jss.v100.i21","url":null,"abstract":"<p><p>This article introduces the R (R Core Team 2019) package <b>BayesCTDesign</b> for two-arm randomized Bayesian trial design using historical control data when available, and simple two-arm randomized Bayesian trial design when historical control data is not available. The package <b>BayesCTDesign</b>, which is available on CRAN, has two simulation functions, historic_sim() and simple_sim() for studying trial characteristics under user defined scenarios, and two methods print() and plot() for displaying summaries of the simulated trial characteristics. The package <b>BayesCTDesign</b> works with two-arm trials with equal sample sizes per arm. The package <b>BayesCTDesign</b> allows a user to study Gaussian, Poisson, Bernoulli, Weibull, Lognormal, and Piecewise Exponential (pwe) outcomes. Power for two-sided hypothesis tests at a user defined alpha is estimated via simulation using a test within each simulation replication that involves comparing a 95% credible interval for the outcome specific treatment effect measure to the null case value. If the 95% credible interval excludes the null case value, then the null hypothesis is rejected, else the null hypothesis is accepted. In the article, the idea of including historical control data in a Bayesian analysis is reviewed, the estimation process of <b>BayesCTDesign</b> is explained, and the user interface is described. Finally, the <b>BayesCTDesign</b> is illustrated via several examples.</p>","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"100 21","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8715862/pdf/nihms-1661326.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39778165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Multiplex social networks are characterized by a common set of actors connected through multiple types of relations. The multinet package provides a set of R functions to analyze multiplex social networks within the more general framework of multilayer networks, where each type of relation is represented as a layer in the network. The package contains functions to import/export, create and manipulate multilayer networks, implementations of several state-of-the-art multiplex network analysis algorithms, e.g., for centrality measures, layer comparison, community detection and visualization. Internally, the package is mainly written in native C++ and integrated with R using the Rcpp package.
{"title":"Analysis of Multiplex Social Networks with R","authors":"Matteo Magnani, L. Rossi, Davide Vega","doi":"10.18637/jss.v098.i08","DOIUrl":"https://doi.org/10.18637/jss.v098.i08","url":null,"abstract":"Multiplex social networks are characterized by a common set of actors connected through multiple types of relations. The multinet package provides a set of R functions to analyze multiplex social networks within the more general framework of multilayer networks, where each type of relation is represented as a layer in the network. The package contains functions to import/export, create and manipulate multilayer networks, implementations of several state-of-the-art multiplex network analysis algorithms, e.g., for centrality measures, layer comparison, community detection and visualization. Internally, the package is mainly written in native C++ and integrated with R using the Rcpp package.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"14 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82013385","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}
Nick Michaud, P. Valpine, Daniel Turek, C. Paciorek, D. Nguyen
nimble is an R package for constructing algorithms and conducting inference on hierarchical models. The nimble package provides a unique combination of flexible model specification and the ability to program model-generic algorithms. Specifically, the package allows users to code models in the BUGS language, and it allows users to write algorithms that can be applied to any appropriate model. In this paper, we introduce the nimbleSMC R package. nimbleSMC contains algorithms for state-space model analysis using sequential Monte Carlo (SMC) techniques that are built using nimble . We first provide an overview of state-space models and commonly-used SMC algorithms. We then describe how to build a state-space model in nimble and conduct inference using existing SMC algorithms within nimbleSMC . SMC algorithms within nimbleSMC currently include the bootstrap filter, auxiliary particle filter, ensemble Kalman filter, IF2 method of iterated filtering, and a particle Markov chain Monte Carlo (MCMC) sampler. These algorithms can be run in R or compiled into C++ for more efficient execution. Examples of applying SMC algorithms to linear autoregressive models and a stochastic volatility model are provided. Finally, we give an overview of how model-generic algorithms are coded within nimble by providing code for a simple SMC algorithm. This illustrates how users can easily extend nimble’s SMC methods in high-level code.
{"title":"Sequential Monte Carlo Methods in the nimble and nimbleSMC R Packages","authors":"Nick Michaud, P. Valpine, Daniel Turek, C. Paciorek, D. Nguyen","doi":"10.18637/jss.v100.i03","DOIUrl":"https://doi.org/10.18637/jss.v100.i03","url":null,"abstract":"nimble is an R package for constructing algorithms and conducting inference on hierarchical models. The nimble package provides a unique combination of flexible model specification and the ability to program model-generic algorithms. Specifically, the package allows users to code models in the BUGS language, and it allows users to write algorithms that can be applied to any appropriate model. In this paper, we introduce the nimbleSMC R package. nimbleSMC contains algorithms for state-space model analysis using sequential Monte Carlo (SMC) techniques that are built using nimble . We first provide an overview of state-space models and commonly-used SMC algorithms. We then describe how to build a state-space model in nimble and conduct inference using existing SMC algorithms within nimbleSMC . SMC algorithms within nimbleSMC currently include the bootstrap filter, auxiliary particle filter, ensemble Kalman filter, IF2 method of iterated filtering, and a particle Markov chain Monte Carlo (MCMC) sampler. These algorithms can be run in R or compiled into C++ for more efficient execution. Examples of applying SMC algorithms to linear autoregressive models and a stochastic volatility model are provided. Finally, we give an overview of how model-generic algorithms are coded within nimble by providing code for a simple SMC algorithm. This illustrates how users can easily extend nimble’s SMC methods in high-level code.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"121 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78438267","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}
Recently, there has been a growing interest in tensor data analysis, where tensor regression is the cornerstone of statistical modeling for tensor data. This package provides the standard least squares estimators and the more efficient envelope estimators for the tensor response regression (TRR) and the tensor predictor regression (TPR) models. Envelope methodology is a relatively new class of dimension reduction techniques that jointly models the regression mean and covariance parameters. Three types of widely applicable envelope estimation algorithms are implemented and applied to both TRR and TPR models.
{"title":"TRES: An R Package for Tensor Regression and Envelope Algorithms","authors":"Jing Zeng, Wenjing Wang, Xin Zhang","doi":"10.18637/jss.v099.i12","DOIUrl":"https://doi.org/10.18637/jss.v099.i12","url":null,"abstract":"Recently, there has been a growing interest in tensor data analysis, where tensor regression is the cornerstone of statistical modeling for tensor data. This package provides the standard least squares estimators and the more efficient envelope estimators for the tensor response regression (TRR) and the tensor predictor regression (TPR) models. Envelope methodology is a relatively new class of dimension reduction techniques that jointly models the regression mean and covariance parameters. Three types of widely applicable envelope estimation algorithms are implemented and applied to both TRR and TPR models.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"25 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83063781","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}
C. Tortora, R. Browne, Aisha Elsherbiny, B. Franczak, P. McNicholas
The MixGHD package for R performs model-based clustering, classification, and discriminant analysis using the generalized hyperbolic distribution (GHD). This approach is suitable for data that can be considered a realization of a (multivariate) continuous random variable. The GHD has the advantage of being flexible due to skewness, concentration, and index parameters; as such, clustering methods that use this distribution are capable of estimating clusters characterized by different shapes. The package provides five different models all based on the GHD, an efficient routine for discriminant analysis, and a function to measure cluster agreement. This paper is split into three parts: the first is devoted to the formulation of each method, extending them for classification and discriminant analysis applications, the second focuses on the algorithms, and the third shows the use of the package on real datasets.
{"title":"Model-Based Clustering, Classification, and Discriminant Analysis Using the Generalized Hyperbolic Distribution: MixGHD R package","authors":"C. Tortora, R. Browne, Aisha Elsherbiny, B. Franczak, P. McNicholas","doi":"10.18637/jss.v098.i03","DOIUrl":"https://doi.org/10.18637/jss.v098.i03","url":null,"abstract":"The MixGHD package for R performs model-based clustering, classification, and discriminant analysis using the generalized hyperbolic distribution (GHD). This approach is suitable for data that can be considered a realization of a (multivariate) continuous random variable. The GHD has the advantage of being flexible due to skewness, concentration, and index parameters; as such, clustering methods that use this distribution are capable of estimating clusters characterized by different shapes. The package provides five different models all based on the GHD, an efficient routine for discriminant analysis, and a function to measure cluster agreement. This paper is split into three parts: the first is devoted to the formulation of each method, extending them for classification and discriminant analysis applications, the second focuses on the algorithms, and the third shows the use of the package on real datasets.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"34 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84220551","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}
Conformal predictors estimate the reliability of outcomes made by supervised machine learning models. Instead of a point value, conformal prediction defines an outcome region that meets a user-specified reliability threshold. Provided that the data are independently and identically distributed, the user can control the level of the prediction errors and adjust it following the requirements of a given application. The quality of conformal predictions often depends on the choice of nonconformity estimate for a given machine learning method. To promote the selection of a successful approach, we have developed Orange3-Conformal, a Python library that provides a range of conformal prediction methods for classification and regression. The library also implements several nonconformity scores. It has a modular design and can be extended to add new conformal prediction methods and nonconformities.
{"title":"Conformal Prediction with Orange","authors":"Tomaz Hocevar, B. Zupan, Jonna C. Stålring","doi":"10.18637/jss.v098.i07","DOIUrl":"https://doi.org/10.18637/jss.v098.i07","url":null,"abstract":"Conformal predictors estimate the reliability of outcomes made by supervised machine learning models. Instead of a point value, conformal prediction defines an outcome region that meets a user-specified reliability threshold. Provided that the data are independently and identically distributed, the user can control the level of the prediction errors and adjust it following the requirements of a given application. The quality of conformal predictions often depends on the choice of nonconformity estimate for a given machine learning method. To promote the selection of a successful approach, we have developed Orange3-Conformal, a Python library that provides a range of conformal prediction methods for classification and regression. The library also implements several nonconformity scores. It has a modular design and can be extended to add new conformal prediction methods and nonconformities.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"2005 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88355408","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}
Recent methodological researches produced permutation methods to test parameters in presence of nuisance variables in linear models or repeated measures ANOVA. Permutation tests are also particularly useful to overcome the multiple comparisons problem as they are used to test the effect of factors or variables on signals while controlling the family-wise error rate (FWER). This article introduces the permuco package which implements several permutation methods. They can all be used jointly with multiple comparisons procedures like the cluster-mass tests or threshold-free cluster enhancement (TFCE). The permuco package is designed, first, for univariate permutation tests with nuisance variables, like regression and ANOVA; and secondly, for comparing signals as required, for example, for the analysis of event-related potential (ERP) of experiments using electroencephalography (EEG). This article describes the permutation methods and the multiple comparisons procedures implemented. A tutorial for each of theses cases is provided.
{"title":"Permutation Tests for Regression, ANOVA, and Comparison of Signals: The permuco Package","authors":"Jaromil Frossard, O. Renaud","doi":"10.18637/jss.v099.i15","DOIUrl":"https://doi.org/10.18637/jss.v099.i15","url":null,"abstract":"Recent methodological researches produced permutation methods to test parameters in presence of nuisance variables in linear models or repeated measures ANOVA. Permutation tests are also particularly useful to overcome the multiple comparisons problem as they are used to test the effect of factors or variables on signals while controlling the family-wise error rate (FWER). This article introduces the permuco package which implements several permutation methods. They can all be used jointly with multiple comparisons procedures like the cluster-mass tests or threshold-free cluster enhancement (TFCE). The permuco package is designed, first, for univariate permutation tests with nuisance variables, like regression and ANOVA; and secondly, for comparing signals as required, for example, for the analysis of event-related potential (ERP) of experiments using electroencephalography (EEG). This article describes the permutation methods and the multiple comparisons procedures implemented. A tutorial for each of theses cases is provided.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"54 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87622264","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}
The R package calculus implements C++ optimized functions for numerical and symbolic calculus, such as the Einstein summing convention, fast computation of the Levi-Civita symbol and generalized Kronecker delta, Taylor series expansion, multivariate Hermite polynomials, high-order derivatives, ordinary differential equations, differential operators and numerical integration in arbitrary orthogonal coordinate systems. The library applies numerical methods when working with R functions or symbolic programming when working with characters or expressions. The package handles multivariate numerical calculus in arbitrary dimensions and coordinates and implements the symbolic counterpart of the numerical methods whenever possible, without depending on external computer algebra systems. Except for Rcpp, the package has no strict dependencies in order to provide a stable self-contained toolbox that invites re-use.
{"title":"calculus: High Dimensional Numerical and Symbolic Calculus in R","authors":"E. Guidotti","doi":"10.18637/jss.v104.i05","DOIUrl":"https://doi.org/10.18637/jss.v104.i05","url":null,"abstract":"The R package calculus implements C++ optimized functions for numerical and symbolic calculus, such as the Einstein summing convention, fast computation of the Levi-Civita symbol and generalized Kronecker delta, Taylor series expansion, multivariate Hermite polynomials, high-order derivatives, ordinary differential equations, differential operators and numerical integration in arbitrary orthogonal coordinate systems. The library applies numerical methods when working with R functions or symbolic programming when working with characters or expressions. The package handles multivariate numerical calculus in arbitrary dimensions and coordinates and implements the symbolic counterpart of the numerical methods whenever possible, without depending on external computer algebra systems. Except for Rcpp, the package has no strict dependencies in order to provide a stable self-contained toolbox that invites re-use.","PeriodicalId":17237,"journal":{"name":"Journal of Statistical Software","volume":"41 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2020-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87161413","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：