Two hundred twenty new packages stuck to CRAN in September. Here are my “Top 40” picks in fourteen categories: Art, Computational Methods, Data, Econometrics, Finance and Insurance, Genomics, Machine Learning, Medicine, Networks and Graphs, Science, Statistics, Time Series, Utilities, and Visualization.
abmR v1.0.4: Supplies tools for running agent-based models (ABM) as discussed in Gochanour et al. (2021) including two movement functions based on the Ornstein-Uhlenbeck model (1930). See the vignette to get started.
SimEngine v1.0.0: Implements functions for structuring, maintaining, running, and debugging statistical simulations on both local and cluster-based computing environments. Emphasis is placed on documentation and scalability. There is an Introduction, an example Power Calculation, and a vignette Comparing SE Estimators.
hockeyR v0.1.1: Provides functions to scrape hockey play-by-play data from NHL.com and Hockey-Reference.com including standings, player stats, and jersey number history. There is a Getting Started Guide and a vignette on Scraping.
yowie v0.1.0: Provides longitudinal wages data sets and several demographic variables from the National Longitudinal Survey of Youth from 1979 to 2018 including: the wages data from the cohort whose highest grade completed is up to high school; the wages data of the high school dropouts and; the demographic data of the cohort in the survey year 1979. See the vignette for details.
COINr v0.5.5: Implements a development environment for composite indicators and scoreboards including utilities for construction (indicator selection, denomination, imputation, data treatment, normalization, weighting and aggregation) and analysis (multivariate analysis, correlation plotting. Look here for an online book, and see the vignette for an extended overview.
spflow v0.1.0: Provides functions to estimate spatial econometric models of origin-destination flows which may exhibit spatial autocorrelation in both the dependent variable and the explanatory variables. See LeSage and Pace (2008) for information on the model, Dargel (2021) for information on the estimation procedures, and the vignette for examples.
Finance and Insurance
DOSPortfolio v0.1.0: Implements dynamic optimal shrinkage estimators for the weights of the global minimum variance portfolio reconstructed at given reallocation points as derived in Bodnar et al. (2021). See the Introduction.
SPLICE v1.0.0: Extends the individual claim simulator SynthETIC to simulate the evolution of case estimates of incurred losses through the lifetime of an insurance claim. See Taylor & Wang (2021) for background and the vignette to get started.
MAnorm2 v1.2.0: Implements a method for normalizing ChIP-seq signals across individual samples or groups of samples and a system of statistical models for calling differential ChIP-seq signals between two or more biological conditions. Refer to Tu et al. (2021) and Chen et al. (2021) for the statistical details. The vignette provides several examples.
morphemepiece v1.0.1: Provides functions to tokenize text into morphemes ether by table lookup or a modified wordpiece tokenization algorithm. There is a vignette on testing the fall-through algorithm and another on Generating a Vocabulary.
NIMAA v0.1.0: Implements a pipeline for nominal data mining, which can effectively find special relationships between data. See Jafari et al. (2021) for a description of the method and the vignette for an introduction.
gapclosing v1.0.2: Provides functions to estimate the disparities across categories (e.g. Black and white) that persists if a treatment variable (e.g. college) is equalized. See Lundberg (2021) for the methodology and the vignette for an overview with examples.
iDOVE v1.3: Implements a nonparametric maximum likelihood method for assessing potentially time-varying vaccine efficacy against SARS-CoV-2 infection under staggered enrollment and time-varying community transmission, allowing crossover of placebo volunteers to the vaccine arm. See Lin et al. (2021) for background and the vignette for the details.
powerly v1.5.2: Implements the sample size computation method for network models proposed by Constantin et al. (2021) which takes the form of a three-step recursive algorithm to find an optimal sample size given a model specification and a performance measure of interest. See README for an example.
Networks and Graphs
multigrapher v0.1.0: Implements methods and models for analyzing multigraphs as introduced by Shafie (2015) including methods to study local and global properties and goodness of fit tests. See Shafle (2016). The vignette provides an introduction.
nevada v0.1.0: Implements a statistical framework for network-valued data analysis which leverages the complexity of the space of distributions on graphs. See Lovato et al. (2020) and Lovato et al. (2021) for the statistical background, and the vignette for an example.
robber v0.2.2: Implementation of a variety of methods to compute the robustness of ecological interaction networks with binary interactions as described in Chabert-Liddell et al. (2021). There is a vignette on Topological Analysis.
argoFloats v1.0.3: Supports the analysis of oceanographic data recorded by Argo autonomous drifting profiling floats. See Kelley et al. (2021) for more on the scientific context and applications. There is an Introduction and a vignette on Quality Control and Adjusted Data.
biosurvey v0.1.1: Provides tools that allow users to plan systems of sampling sites with the goals of increasing the efficiency of biodiversity monitoring. See Arita et al. (2011) and Soberón & Cavner (2015) for background. There are vignettes on Preparing Data, Selecting Sample Sites, Using Preselected Points, and Testing Efficacy of Selected Sites.
HostSwitch v0.1.0: Provides functions to aims to investigate the dynamics of the host switch in the population of an organism that interacts with current and potential hosts over generations. The underlying model is based on Araujo et al. (2015). See the vignette for an example.
cvam v0.9.2: Extends R’s implementation of categorical variables (factors) to handle coarsened observations and implements log-linear models for coarsened categorical data, including latent-class models. There is a vignette describing Coarsened Factors and another on Fitting Log-linear Models.
JustifyAlpha v0.1.1: Provides functions to justify alpha levels for statistical hypothesis tests by avoiding Lindley’s paradox, or by minimizing or balancing error rates. See Maier & Lakens (2021) for the theory and the vignette for an introduction.
spatialRF v1.1.3: Implements methods to automatically generate and select spatial predictors for spatial regression with Random Forest. See Dray et al. (2006) and RFsp Hengl et al. (2017). Look here for documentation and examples.
vdra v1.0.0: Implements three protocols for performing secure linear, logistic, and Cox regression on vertically partitioned data across several data partners in such a way that data is not shared among data partners. See Slavkovic et. al. (2007) for background. There is an Introduction and vignettes on Using PopMedNet, Communications and Files, and Workflow.
colorblindcheck v1.0.0: Provides functions to compare color palettes with simulations of color vision deficiencies – deuteranopia, protanopia, and tritanopia. It includes a calculation of distances between colors and creates summaries of differences between color palettes and simulations of color vision deficiencies. See the post by G. Aisch for background and the vignette for details.
httr2 v0.1.1: Implements tools for creating and modifying HTTP requests, executing them, and then processing the results.
httr2 is a modern re-imagining of
httr that uses a pipe-based interface and solves more of the problems that API wrapping packages face. See the vignettes httr2 and Wrapping APIs.
bittermelon v0.1.3: Provides functions for creating and modifying bitmaps with special emphasis on bitmap fonts and their glyphs including native read/write support for the
yaff bitmap font formats. Look here for documentation.
semptools v0.2.9.3: Implements functions for customizing structural equation plots that can be chained using a pipe operator. There is a Quick Start Guide, and vignettes on Nodes, Matrix Layout, CFA, and SEM.