Digital Commons Network^™

Basis-Adaptive Selection Algorithm In Dr-Package, Jae Keun Yoo

The R Journal

Sufficient dimension reduction (SDR) turns out to be a useful dimension reduction tool in high-dimensional regression analysis. Weisberg (2002) developed the dr-package to implement the four most popular SDR methods. However, the package does not provide any clear guidelines as to which method should be used given a data. Since the four methods may provide dramatically different dimension reduction results, the selection in the dr-package is problematic for statistical practitioners. In this paper, a basis-adaptive selection algorithm is developed in order to relieve this issue. The basic idea is to select an SDR method that provides the highest …

Rcss: R Package For Optimal Convex Stochastic Switching, Juri Hinz, Jeremy Yee

The R Journal

The R package rcss provides users with a tool to approximate the value functions in the Bellman recursion under certain assumptions that guarantee desirable convergence properties. This R package represents the first software implementation of these methods using matrices and nearest neighbors. This package also employs a pathwise dynamic method to gauge the quality of these value function approximations. Statistical analysis can be performed on the results to obtain other useful practical insights. This paper describes rcss version 1.6.

Idmtpreg: Regression Model For Progressive Illness Death Data, Leyla Azarang, Manuel Oviedo De La Fuente

The R Journal

The progressive illness-death model is frequently used in medical applications. For example, the model may be used to describe the disease process in cancer studies. We have developed a new R package called idmTPreg to estimate regression coefficients in datasets that can be described by the progressive illness-death model. The motivation for the development of the package is a recent contribution that enables the estimation of possibly time-varying covariate effects on the transition probabilities for a progressive illness-death data. The main feature of the package is that it befits both non-Markov and Markov progressive illness-death data. The package implements the …

Conference Report: R / Medicine Report, Joseph Rickert, Naras Balasubramanian, Michael Kane

The R Journal

R has found widespread use and is flourishing in bioinformatics, the pharmaceutical industry, clinical trials, and basic science labs. While R is being adopted in clinical informatics, its potential has not yet been realized. We believe R will fundamentally transform the space because of its strengths in making new methods available, the availability of tools for reproducible research, its interfaces to other languages, and it’s ability to disseminate new approaches through web interfaces and packaging for rapid prototyping of ideas and implementations.

Moreover, while large number of clinicians, scientists, and statisticians contribute to data driven medical science, communication between individuals …

Conference Report: Ser Iii, Ariel Levy, Luciane F. Alcoforado, Orlando Celso Longo

The R Journal

SER is a multidisciplinary event, which integrates professionals, students, and practioners from most diversified knowledge areas who make use of data analysis. The first edition took place on May 2016 as the initiative of a group of professors from the Fluminense Federal University, partners of other Institutions, and was supported by CAPES (Coordination for higher Education Staff Development). SER event was recognized by the R foundation (2018)1 for its pioneering in Latin America in bringing together an expressive number of R users.

News From The Bioconductor Project, Bioconductor Core Team

The R Journal

The Bioconductor project provides tools for the analysis and comprehension of high-throughput genomic data. Bioconductor 3.8 was released on 31 October, 2018. It is compatible with R 3.5.2 and consists of 1649 software packages, 360 experiment data packages, and 941 up-to-date annotation packages. The release announcement includes descriptions of 95 new software packages and updated NEWS files for many additional packages.

Navigating The R Package Universe, Julia Silge, John C. Nash, Spencer Graves

The R Journal

Today, the enormous number of contributed packages available to R users outstrips any given user’s ability to understand how these packages work, their relative merits, or how they are related to each other. We organized a plenary session at useR!2017 in Brussels for the R community to think through these issues and ways forward. This session considered three key points of discussion. Users can navigate the universe of R packages with (1) capabilities for directly searching for R packages, (2) guidance for which packages to use, e.g., from CRAN Task Views and other sources, and (3) access to commoninterfaces for …

Consistency Cubes: A Fast, Efficient Method For Exact Boolean Minimization, Adrian Dusa

The R Journal

A lot of effort has been spent over the past few decades in the QCA methodology field, to develop efficient Boolean minimization algorithms to derive an exact,and more importantly complete list of minimal prime implicants that explain the initial, observed positive configurations.

As the complexity grows exponentially with every new condition, the required computer memory goes past the current computer resources and the polynomial time required to solve this problem quickly grows towards infinity.

This paper introduces a new alternative to the existing non-polynomial attempts. It completely solves the memory problem, and preliminary tests show it is exponentially hundreds of …

Conference Report: R / Pharma 2018, Joseph Rickert

The R Journal

The R / Pharma conference began as grass-roots initiative led by data scientists working in the pharmaceutical industry to promote the use of R in Pharma, and to establish and share best practices. The founding members organized the project as an R Consortium working group, and undertook the ambitious task of launching an annual conference envisioned as a relatively small, collegial, industry-oriented event with a strong scientific program.

Forecast Combinations In R Using The Forecastcomb Package, Christoph E. Weiss, Eran Raviv, Gernot Roetzer

The R Journal

This paper introduces the R package ForecastComb. The aim is to provide researchers and practitioners with a comprehensive implementation of the most common ways in which forecasts can be combined. The package in its current version covers 15 popular estimation methods for creating a combined forecasts – including simple methods, regression-based methods, and eigenvector-based methods. It also includes useful tools to deal with common challenges of forecast combination (e.g., missing values in component forecasts, or multicollinearity), and to rationalize and visualize the combination results.

The Politeness Package: Detecting Politeness In Natural Language, Michael Yeomans, Alejandro Kantor, Dustin Tingley

The R Journal

This package provides tools to extract politeness markers in English natural language. It also allows researchers to easily visualize and quantify politeness between groups of documents. This package combines and extends prior research on the linguistic markers of politeness (Brown and Levinson, 1987; Danescu-Niculescu-Mizil et al., 2013; Voigt et al., 2017). We demonstrate two applications for detecting politeness in natural language during consequential social interactions— distributive negotiations, and speed dating.

Jsr223: A Java Platform Integration For R With Programming Languages Groovy, Javascript, Jruby, Jython, And Kotlin, Floid R. Gilbert, David B. Dahl

The R Journal

The R package jsr223 is a high-level integration for five programming languages in the Java platform: Groovy, JavaScript, JRuby, Jython, and Kotlin. Each of these languages can use Java objects in their own syntax. Hence, jsr223 is also an integration for R and the Java platform. It enables developers to leverage Java solutions from within R by embedding code snippets or evaluating script f iles. This approach is generally easier than rJava’s low-level approach that employs the Java Native Interface. jsr223’s multi-language support is dependent on the Java Scripting API: an implementation of “JSR-223: Scripting for the Java …

Rcppmsgpack: Messagepack Headers And Interface Functions For R, Travers Ching, Dirk Eddelbuettel

The R Journal

MessagePack, or MsgPack for short, or when referring to the implementation, is an efficient binary serialization format for exchanging data between different programming languages. The RcppMsgPack package provides R with both the MessagePack C++ header files, and the ability to access, create and alter MessagePack objects directly from R. The main driver functions of the R interface are two functions msgpack_pack and msgpack_unpack. The function msgpack_pack serializes Robjects to a raw MessagePack message. The function msgpack_unpack de-serializes MessagePack messages back into R objects. Several helper functions are available to aid in processing and formatting data including msgpack_simplify, msgpack_format and msgpack_map

Changes On Cran, Kurt Hornik, Uwe Ligges, Achim Zeileis

The R Journal

In the past 6 months, 1029 new packages were added to the CRAN package repository. 68 packages were unarchived, 122 archived, and one removed. The following shows the growth of the number of active packages in the CRAN package repository

Rfsa: An R Package For Finding Best Subsets And Interactions, Joshua Lambert, Liyu Gong, Corrine F. Elliott, Katherine Thompson, Arnold Stromberg

The R Journal

Herein we present the R package rFSA, which implements an algorithm for improved variable selection. The algorithm searches a data space for models of a user-specified form that are statistically optimal under a measure of model quality. Many iterations afford a set of feasible solutions (or candidate models) that the researcher can evaluate for relevance to his or her questions of interest. The algorithm can be used to formulate new or to improve upon existing models in bioinformatics, health care, and myriad other fields in which the volume of available data has outstripped researchers’ practical and computational ability to explore …

Revengc: An R Package To Reverse Engineer Summarized Data, Samantha Duchscherer, Robert Stewart, Marie Urban

The R Journal

Decoupled (e.g. separate averages) and censored (e.g. > 100 species) variables are continually reported by many well-established organizations, such as the World Health Organization (WHO), Centers for Disease Control and Prevention (CDC), and World Bank. The challenge therefore is to infer what the original data could have been given summarized information. We present an R package that reverse engineers censored and/or decoupled data with two main functions. The cnbinom.pars() function estimates the average and dispersion parameter of a censored univariate frequency table. The rec() function reverse engineers summarized data into an uncensored bivariate table of probabilities.

Ggplot2 Compatible Quantile-Quantile Plots In, Alexandre Almeida, Adam Loy, Heike Hofmann

The R Journal

Q-Q plots allow us to assess univariate distributional assumptions by comparing a set of quantiles from the empirical and the theoretical distributions in the form of a scatterplot. To aid in the interpretation of Q-Q plots, reference lines and confidence bands are often added. We can also detrend the Q-Q plot so the vertical comparisons of interest come into focus. Various implementations of Q-Q plots exist in R, but none implements all of these features. qqplotr extends ggplot2 to provide a complete implementation of Q-Q plots. This paper introduces the plotting framework provided by qqplotr and provides multiple examples of …

Measurement Errors In R, Iñaki Ucar, Edzer Pebesma, Arturo Azcorra

The R Journal

This paper presents an R package to handle and represent measurements with errors in a very simple way. We briefly introduce the main concepts of metrology and propagation of uncertainty, and discuss related R packages. Building upon this, we introduce the errors package, which provides a class for associating uncertainty metadata, automated propagation and reporting. Working with errors enables transparent, lightweight, less error-prone handling and convenient representation of measurements with errors. Finally, we discuss the advantages, limitations and future work of computing with errors.

Spatial Uncertainty Propagation Analysis With The Spup R Package, Kasia Sawicka, Gerard B.M. Heuvelink, Dennis J.J. Walvoort

The R Journal

Many environmental and geographical models, such as those used in land degradation, agroecological and climate studies, make use of spatially distributed inputs that are known imperfectly. The R package spup provides functions for examining the uncertainty propagation from input data and model parameters onto model outputs via the environmental model. The functions include uncertainty model specification, stochastic simulation and propagation of uncertainty using Monte Carlo (MC) techniques. Uncertain variables are described by probability distributions. Both numerical and categorical data types are handled. The package also accommodates spatial auto-correlation within a variable and cross-correlation between variables. The MC realizations may be …

The Utiml Package: Multi-Label Classification In R, Adriano Rivolli, Andre C.P.L.F. De Carvalho

The R Journal

Learning classification tasks in which each instance is associated with one or more labels are known as multi-label learning. The implementation of multi-label algorithms, performed by different researchers, have several specificities, like input/output format, different internal functions, distinct programming language, to mention just some of them. As a result, current machine learning tools include only a small subset of multi-label decomposition strategies. The utiml package is a framework for the application of classification algorithms to multi-label data. Like the well known MULAN used with Weka, it provides a set of multi-label procedures such as sampling methods, transformation strategies, threshold functions, …

Nsroc: An R Package For Non-Standard Roc Curve Analysis, Sonia Pérez-Fernández, Pablo Martínez-Camblor, Peter Filzmoser, Norberto Corral

The R Journal

The receiver operating characteristic (ROC) curve is a graphical method which has become standard in the analysis of diagnostic markers, that is, in the study of the classification ability of a numerical variable. Most of the commercial statistical software provide routines for the standard ROC curve analysis. Of course, there are also many R packages dealing with the ROC estimation as well as other related problems. In this work we introduce the nsROC package which incorporates some new ROC curve procedures. Particularly: ROC curve comparison based on general distances among functions for both paired and unpaired designs; efficient confidence bands …

Stilt: Easy Emulation Of Time Series Ar(1) Computer Model Output In Multidimensional Parameter Space, Roman Olson, Kelsey L. Ruckert, Won Chang, Klaus Keller, Murali Haran, Soon-Il An

The R Journal

Statistically approximating or “emulating” time series model output in parameter space is a common problem in climate science and other fields. There are many packages for spatio-temporal modeling. However, they often lack focus on time series, and exhibit statistical complexity. Here, we present the R package stilt designed for simplified AR(1) time series Gaussian process emulation, and provide examples relevant to climate modelling. Notably absent is Markov chain Monte Carlo estimation – a challenging concept to many scientists. We keep the number of user choices to a minimum. Hence, the package can be useful pedagogically, while still applicable to real …

R Foundation News, Torsten Hothorn

The R Journal

Donations and members

Donations

Supporting benefactors

Supporting institutions

Supporting members

Sarima Analysis And Automated Model Reports With Bets, An R Package, Talitha F. Speranza, Pedro C. Ferreira, Jonatha A. Da Costa

The R Journal

This article aims to demonstrate how the powerful features of the R package BETS can be applied to SARIMA time series analysis. BETS provides not only thousands of Brazilian economic time series from different institutions, but also a range of analytical tools, and educational resources. In particular, BETS is capable of generating automated model reports for any given time series. These reports rely on a single function call and are able to build three types of models (SARIMA being one of them). The functions need few inputs and output rich content. The output varies according to the inputs and usually …

Profile Likelihood Estimation Of The Correlation Coefficient In The Presence Of Left, Right Or Interval Censoring And Missing Data, Yanming Li, Brenda W. Gillespie, Kerby Shedden, John A. Gillespie

The R Journal

We discuss implementation of a profile likelihood method for estimating a Pearson correlation coefficient from bivariate data with censoring and/or missing values. The method is implemented in an R package clikcorr which calculates maximum likelihood estimates of the correlation coefficient when the data are modeled with either a Gaussian or a Student t-distribution, in the presence of left, right, or interval censored and/or missing data. The R package includes functions for conducting inference and also provides graphical functions for visualizing the censored data scatter plot and profile log likelihood function. The performance of clikcorr in a variety of circumstances is …

Dot-Pipe: An S3 Extensible Pipe For R, John Mount, Nina Zumel

The R Journal

Pipe notation is popular with a large league of R users, with magrittr being the dominant realization. However, this should not be enough to consider piping in R as a settled topic that is not subject to further discussion, experimentation, or possibility for improvement. To promote innovation opportunities, we describe the wrapr R package and “dot-pipe” notation, a well behaved sequencing operator with S3 extensibility. We include a number of examples of using this pipe to interact with and extend other R packages.

Clustmixtype: User-Friendly Clustering Of Mixed-Type Data In R, Gero Szepannek

The R Journal

Clustering algorithms are designed to identify groups in data where the traditional emphasis has been on numeric data. In consequence, many existing algorithms are devoted to this kind of data even though a combination of numeric and categorical data is more common in most business applications. Recently, new algorithms for clustering mixed-type data have been proposed based on Huang’s k-prototypes algorithm. This paper describes the R package clustMixType which provides an implementation of k-prototypes in R.

Editorial, John Verzani

The R Journal

On behalf of the editorial board, I am pleased to present Volume 10, Issue 2 of the R Journal.

This issue covers a wide range of topics through its 37 articles. As is typical, many of these are related to packages that provide tools for new statistical modeling in R. Examples in this issue include "clustMixType: User-Friendly Clustering of Mixed-Type Data in R" by Szepannek and "BNSP: an R Package for Fitting Bayesian Semiparametric Regression Models and Variable Selection" by Papageorgiou.

Downside Risk Evaluation With The R Package Gas, David Ardia, Kris Boudt, Leopoldo Catania

The R Journal

Financial risk managers routinely use non–linear time series models to predict the downside risk of the capital under management. They also need to evaluate the adequacy of their model using so–called backtesting procedures. The latter involve hypothesis testing and evaluation of loss functions. This paper shows how the R package GAS can be used for both the dynamic prediction and the evaluation of downside risk. Emphasis is given to the two key financial downside risk measures: Value-at-Risk (VaR) and Expected Shortfall (ES). High-level functions for: (i) prediction, (ii) backtesting, and (iii) model comparison are discussed, and code examples are provided. …

Explanations Of Model Predictions With Live And Breakdown Packages, Mateusz Staniak, Przemysław Biecek

The R Journal

Complex models are commonly used in predictive modeling. In this paper we present R packages that can be used for explaining predictions from complex black box models and attributing parts of these predictions to input features. We introduce two new approaches and corresponding packages for such attribution, namely live and breakDown. We also compare their results with existing implementations of state-of-the-art solutions, namely, lime (Pedersen and Benesty, 2018) which implements Locally Interpretable Model-agnostic Explanations and iml (Molnar et al., 2018) which implements Shapley values.