Journal of Statistical Software
Not a member yet
1629 research outputs found
Sort by
RecordTest: An R Package to Analyze Non-Stationarity in the Extremes Based on Record-Breaking Events
Get PDFThe study of non-stationary behavior in the extremes is important to analyze data in environmental sciences, climate, finance, or sports. As an alternative to the classical extreme value theory, this analysis can be based on the study of record-breaking events. The R package RecordTest provides a useful framework for non-parametric analysis of non-stationary behavior in the extremes, based on the analysis of records. The underlying idea of all the non-parametric tools implemented in the package is to use the distribution of the record occurrence under series of independent and identically distributed continuous random variables, to analyze if the observed records are compatible with that behavior. Two families of tests are implemented. The first only requires the record times of the series, while the second includes more powerful tests that join the information from different types of records: upper and lower records in the forward and backward series. The package also offers functions that cover all the steps in this type of analysis such as data preparation, identification of the records, exploratory analysis, and complementary graphical tools. The applicability of the package is illustrated with the analysis of the effect of global warming on the extremes of the daily maximum temperature series in Zaragoza, Spain
REndo: Internal Instrumental Variables to Address Endogeneity
Get PDFEndogeneity is a common problem in any causal analysis. It arises when the independence assumption between an explanatory variable and the error in a statistical model is violated. The causes of endogeneity are manifold and include response bias in surveys, omission of important explanatory variables, or simultaneity between explanatory and response variables. Instrumental variable estimation provides a possible solution. However, valid and strong external instruments are difficult to find. Consequently, internal instrumental variable approaches have been proposed to correct for endogeneity without relying on external instruments. The R package REndo implements various internal instrumental variable approaches, i.e., latent instrumental variables estimation (Ebbes, Wedel, Boeckenholt, and Steerneman 2005), higher moments estimation (Lewbel 1997), heteroscedastic error estimation (Lewbel 2012), joint estimation using copula (Park and Gupta 2012) and multilevel generalized method of moments estimation (Kim and Frees 2007). Package usage is illustrated on simulated and real-world data
DataFrames.jl: Flexible and Fast Tabular Data in Julia
Get PDFDataFrames.jl is a package written for and in the Julia language offering flexible and efficient handling of tabular data sets in memory. Thanks to Julia's unique strengths, it provides an appealing set of features: Rich support for standard data processing tasks and excellent flexibility and efficiency for more advanced and non-standard operations. We present the fundamental design of the package and how it compares with implementations of data frames in other languages, its main features, performance, and possible extensions. We conclude with a practical illustration of typical data processing operations
Efficient Multiple Imputation for Diverse Data in Python and R: MIDASpy and rMIDAS
Get PDFThis paper introduces software packages for efficiently imputing missing data using deep learning methods in Python (MIDASpy) and R (rMIDAS). The packages implement a recently developed approach to multiple imputation known as MIDAS, which involves introducing additional missing values into the dataset, attempting to reconstruct these values with a type of unsupervised neural network known as a denoising autoencoder, and using the resulting model to draw imputations of originally missing data. These steps are executed by a fast and flexible algorithm that expands both the quantity and the range of data that can be analyzed with multiple imputation. To help users optimize the algorithm for their particular application, MIDASpy and rMIDAS offer a host of user-friendly tools for calibrating and validating the imputation model. We provide a detailed guide to these functionalities and demonstrate their usage on a large real dataset
intRinsic: An R Package for Model-Based Estimation of the Intrinsic Dimension of a Dataset
Get PDFThis article illustrates intRinsic, an R package that implements novel state-of-the-art likelihood-based estimators of the intrinsic dimension of a dataset, an essential quantity for most dimensionality reduction techniques. In order to make these novel estimators easily accessible, the package contains a small number of high-level functions that rely on a broader set of efficient, low-level routines. Generally speaking, intRinsic encompasses models that fall into two categories: homogeneous and heterogeneous intrinsic dimension estimators. The first category contains the two nearest neighbors estimator, a method derived from the distributional properties of the ratios of the distances between each data point and its first two closest neighbors. The functions dedicated to this method carry out inference under both the frequentist and Bayesian frameworks. In the second category, we find the heterogeneous intrinsic dimension algorithm, a Bayesian mixture model for which an efficient Gibbs sampler is implemented. After presenting the theoretical background, we demonstrate the performance of the models on simulated datasets. This way, we can facilitate the exposition by immediately assessing the validity of the results. Then, we employ the package to study the intrinsic dimension of the Alon dataset, obtained from a famous microarray experiment. Finally, we show how the estimation of homogeneous and heterogeneous intrinsic dimensions allows us to gain valuable insights into the topological structure of a dataset
Modeling Population Growth in R with the biogrowth Package
Get PDFThe growth of populations is of interest in a broad variety of fields, such as epidemiology, economics or biology. Although a large variety of growth models are available in the scientific literature, their application usually requires advanced knowledge of mathematical programming and statistical inference, especially when modelling growth under dynamic environmental conditions. This article presents the biogrowth package for R, which implements functions for modelling the growth of populations. It can predict growth under static or dynamic environments, considering the effect of an arbitrary number of environmental factors. Moreover, it can be used to fit growth models to data gathered under static or dynamic environmental conditions. The package allows the user to fix any model parameter prior to the fit, an approach that can mitigate identifiability issues associated to growth models. The package includes common S3 methods for visualization and statistical analysis (summary of the fit, predictions, . . . ), easing result interpretation. It also includes functions for model comparison/selection. We illustrate the functions in biogrowth using examples from food science and economy
cglasso: An R Package for Conditional Graphical Lasso Inference with Censored and Missing Values
Get PDFSparse graphical models have revolutionized multivariate inference. With the advent of high-dimensional multivariate data in many applied fields, these methods are able to detect a much lower-dimensional structure, often represented via a sparse conditional independence graph. There have been numerous extensions of such methods in the past decade. Many practical applications have additional covariates or suffer from missing or censored data. Despite the development of these extensions of sparse inference methods for graphical models, there have been so far no implementations for, e.g., conditional graphical models. Here we present the general-purpose package cglasso for estimating sparse conditional Gaussian graphical models with potentially missing or censored data. The method employs an efficient expectation-maximization estimation of an ℓ1 -penalized likelihood via a block-coordinate descent algorithm. The package has a user-friendly data manipulation interface. It estimates a solution path and includes various automatic selection algorithms for the two ℓ1 tuning parameters, associated with the sparse precision matrix and sparse regression coefficients, respectively. The package pays particular attention to the visualization of the results, both by means of marginal tables and figures, and of the inferred conditional independence graphs. This package provides a unique and computational efficient implementation of a conditional Gaussian graphical model that is able to deal with the additional complications of missing and censored data. As such it constitutes an important contribution for empirical scientists wishing to detect sparse structures in high-dimensional data
Bayesian Structure Learning and Sampling of Bayesian Networks with the R Package BiDAG
Get PDFThe R package BiDAG implements Markov chain Monte Carlo (MCMC) methods for structure learning and sampling of Bayesian networks. The package includes tools to search for a maximum a posteriori (MAP) graph and to sample graphs from the posterior distribution given the data. A new hybrid approach to structure learning enables inference in large graphs. In the first step, we define a reduced search space by means of the PC algorithm or based on prior knowledge. In the second step, an iterative order MCMC scheme proceeds to optimize the restricted search space and estimate the MAP graph. Sampling from the posterior distribution is implemented using either order or partition MCMC. The models and algorithms can handle both discrete and continuous data. The BiDAG package also provides an implementation of MCMC schemes for structure learning and sampling of dynamic Bayesian networks
drda: An R Package for Dose-Response Data Analysis Using Logistic Functions
Get PDFAnalysis of dose-response data is an important step in many scientific disciplines, including but not limited to pharmacology, toxicology, and epidemiology. The R package drda is designed to facilitate the analysis of dose-response data by implementing efficient and accurate functions with a familiar interface. With drda it is possible to fit models by the method of least squares, perform goodness-of-fit tests, and conduct model selection. Compared to other similar packages, drda provides in general more accurate estimates in the least-squares sense. This result is achieved by a smart choice of the starting point in the optimization algorithm and by implementing the Newton method with a trust region with analytical gradients and Hessian matrices. In this article, drda is presented through the description of its methodological components and examples of its user-friendly functions. Performance is evaluated using both synthetic data and a real, large-scale drug sensitivity screening dataset
netmeta: An R Package for Network Meta-Analysis Using Frequentist Methods
Get PDFNetwork meta-analysis compares different interventions for the same condition, by combining direct and indirect evidence derived from all eligible studies. Network metaanalysis has been increasingly used by applied scientists and it is a major research topic for methodologists. This article describes the R package netmeta, which adopts frequentist methods to fit network meta-analysis models. We provide a roadmap to perform network meta-analysis, along with an overview of the main functions of the package. We present three worked examples considering different types of outcomes and different data formats to facilitate researchers aiming to conduct network meta-analysis with netmeta