Computes Chernoff's distribution based on the method in Piet Groeneboom & Jon A Wellner (2001) Computing Chernoff's Distribution, Journal of Computational and Graphical Statistics, 10:2, 388-400, <doi:10.1198/10618600152627997>. Chernoff's distribution is defined as the distribution of the maximizer of the two-sided Brownian motion minus quadratic drift. That is, Z = argmax (B(t)-t^2).

Stan based functions to estimate CAR-MM models. These models allow to estimate Generalised Linear Models with CAR (conditional autoregressive) spatial random effects for spatially and temporally misaligned data, provided a suitable Multiple Membership matrix. The main references are Gramatica, Liverani and Congdon (2023) <doi:10.1214/23-BA1370>, Petrof, Neyens, Nuyts, Nackaerts, Nemery and Faes (2020) <doi:10.1002/sim.8697> and Gramatica, Congdon and Liverani <doi:10.1111/rssc.12480>.

It has been designed to calculate the required sample size in randomized clinical trials with composite endpoints. It also calculates the expected effect and the probability of observing the composite endpoint, among others. The methodology can be found in Bofill & Gómez (2019) <doi:10.1002/sim.8092> and Gómez & Lagakos (2013) <doi:10.1002/sim.5547>.

This package provides a flexible interface for interacting with Large Language Model ('LLM') providers including OpenAI', Azure OpenAI', Azure AI Foundry', Groq', Anthropic', DeepSeek', DashScope', Gemini', Grok', GitHub Models', and AWS Bedrock. Supports both synchronous and asynchronous chat-completion APIs, with features such as retry logic, dynamic model selection, customizable parameters, and multi-message conversation handling. Designed to streamline integration with state-of-the-art LLM services across multiple platforms.

Duplicated publication data (pre-processed and formatted) for entity resolution. This data set contains a total of 1879 records. The following variables are included in the data set: id, title, book title, authors, address, date, year, editor, journal, volume, pages, publisher, institution, type, tech, note. The data set has a respective gold data set that provides information on which records match based on id.

It is an open source insurance claim simulation engine sponsored by the Casualty Actuarial Society. It generates individual insurance claims including open claims, reopened claims, incurred but not reported claims and future claims. It also includes claim data fitting functions to help set simulation assumptions. It is useful for claim level reserving analysis. Parodi (2013) <https://www.actuaries.org.uk/documents/triangle-free-reserving-non-traditional-framework-estimating-reserves-and-reserve-uncertainty>.

This package provides a set of state-of-the-art probabilistic modeling approaches to derive estimates of individual customer lifetime values (CLV). Commonly, probabilistic approaches focus on modelling 3 processes, i.e. individuals attrition, transaction, and spending process. Latent customer attrition models, which are also known as "buy-'til-you-die models", model the attrition as well as the transaction process. They are used to make inferences and predictions about transactional patterns of individual customers such as their future purchase behavior. Moreover, these models have also been used to predict individualsâ long-term engagement in activities such as playing an online game or posting to a social media platform. The spending process is usually modelled by a separate probabilistic model. Combining these results yields in lifetime values estimates for individual customers. This package includes fast and accurate implementations of various probabilistic models for non-contractual settings (e.g., grocery purchases or hotel visits). All implementations support time-invariant covariates, which can be used to control for e.g., socio-demographics. If such an extension has been proposed in literature, we further provide the possibility to control for time-varying covariates to control for e.g., seasonal patterns. Currently, the package includes the following latent attrition models to model individuals attrition and transaction process: [1] Pareto/NBD model (Pareto/Negative-Binomial-Distribution), [2] the Extended Pareto/NBD model (Pareto/Negative-Binomial-Distribution with time-varying covariates), [3] the BG/NBD model (Beta-Gamma/Negative-Binomial-Distribution) and the [4] GGom/NBD (Gamma-Gompertz/Negative-Binomial-Distribution). Further, we provide an implementation of the Gamma/Gamma model to model the spending process of individuals.

Cointegration methods are widely used in empirical macroeconomics and empirical finance. It is well known that in a cointegrating regression the ordinary least squares (OLS) estimator of the parameters is super-consistent, i.e. converges at rate equal to the sample size T. When the regressors are endogenous, the limiting distribution of the OLS estimator is contaminated by so-called second order bias terms, see e.g. Phillips and Hansen (1990) <DOI:10.2307/2297545>. The presence of these bias terms renders inference difficult. Consequently, several modifications to OLS that lead to zero mean Gaussian mixture limiting distributions have been proposed, which in turn make standard asymptotic inference feasible. These methods include the fully modified OLS (FM-OLS) approach of Phillips and Hansen (1990) <DOI:10.2307/2297545>, the dynamic OLS (D-OLS) approach of Phillips and Loretan (1991) <DOI:10.2307/2298004>, Saikkonen (1991) <DOI:10.1017/S0266466600004217> and Stock and Watson (1993) <DOI:10.2307/2951763> and the new estimation approach called integrated modified OLS (IM-OLS) of Vogelsang and Wagner (2014) <DOI:10.1016/j.jeconom.2013.10.015>. The latter is based on an augmented partial sum (integration) transformation of the regression model. IM-OLS is similar in spirit to the FM- and D-OLS approaches, with the key difference that it does not require estimation of long run variance matrices and avoids the need to choose tuning parameters (kernels, bandwidths, lags). However, inference does require that a long run variance be scaled out. This package provides functions for the parameter estimation and inference with all three modified OLS approaches. That includes the automatic bandwidth selection approaches of Andrews (1991) <DOI:10.2307/2938229> and of Newey and West (1994) <DOI:10.2307/2297912> as well as the calculation of the long run variance.

An implementation of the clugen algorithm for generating multidimensional clusters with arbitrary distributions. Each cluster is supported by a line segment, the position, orientation and length of which guide where the respective points are placed. This package is described in Fachada & de Andrade (2023) <doi:10.1016/j.knosys.2023.110836>.

This package provides tools for downloading, reading and analyzing the COVID19 National Household Sample Survey - PNAD COVID19, a household survey from Brazilian Institute of Geography and Statistics - IBGE. The data must be downloaded from the official website <https://www.ibge.gov.br/>. Further analysis must be made using package survey'.

Classification method described in Dancik et al (2011) <doi:10.1158/0008-5472.CAN-11-2427> that classifies a sample according to the class with the maximum mean (or any other function of) correlation between the test and training samples with known classes.

Interface to interest and foreign exchange rates published by the Czech National Bank.

Set of tools to compute metrics and indices for climate analysis. The package provides functions to compute extreme indices, evaluate the agreement between models and combine theses models into an ensemble. Multi-model time series of climate indices can be computed either after averaging the 2-D fields from different models provided they share a common grid or by combining time series computed on the model native grid. Indices can be assigned weights and/or combined to construct new indices. The package makes use of some of the methods described in: N. Manubens et al. (2018) <doi:10.1016/j.envsoft.2018.01.018>.

Combines taxonomic classifications of high-throughput 16S rRNA gene sequences with reference proteomes of archaeal and bacterial taxa to generate amino acid compositions of community reference proteomes. Calculates chemical metrics including carbon oxidation state ('Zc'), stoichiometric oxidation and hydration state ('nO2 and nH2O'), H/C, N/C, O/C, and S/C ratios, grand average of hydropathicity ('GRAVY'), isoelectric point ('pI'), protein length, and average molecular weight of amino acid residues. Uses precomputed reference proteomes for archaea and bacteria derived from the Genome Taxonomy Database ('GTDB'). Also includes reference proteomes derived from the NCBI Reference Sequence ('RefSeq') database and manual mapping from the RDP Classifier training set to RefSeq taxonomy as described by Dick and Tan (2023) <doi:10.1007/s00248-022-01988-9>. Processes taxonomic classifications in RDP Classifier format or OTU tables in phyloseq-class objects from the Bioconductor package phyloseq'.

Tables summarizing clinical trial results are often complex and require detailed tailoring prior to submission to a health authority. The crane package supplements the functionality of the gtsummary package for creating these often highly bespoke tables in the pharmaceutical industry.

Tests convergence in macro-financial panels combining Dynamic Factor Models (DFM) and mean-reverting Ornstein-Uhlenbeck (OU) processes. Provides: (i) static/approximate DFMs for large panels with VAR/VECM stability checks, Portmanteau tests and rolling out-of-sample R^2, following Stock and Watson (2002) <doi:10.1198/073500102317351921> and the Generalized Dynamic Factor Model of Forni, Hallin, Lippi and Reichlin (2000) <doi:10.1162/003465300559037>; (ii) cointegration analysis à la Johansen (1988) <doi:10.1016/0165-1889(88)90041-3>; (iii) OU-based convergence and half-life summaries grounded in Uhlenbeck and Ornstein (1930) <doi:10.1103/PhysRev.36.823> and Vasicek (1977) <doi:10.1016/0304-405X(77)90016-2>; (iv) robust inference via sandwich HC/HAC estimators (Zeileis (2004) <doi:10.18637/jss.v011.i10>) and regression diagnostics ('lmtest'); and (v) optional PLS-based factor preselection (Mevik and Wehrens (2007) <doi:10.18637/jss.v018.i02>). Functions emphasize reproducibility and clear, publication-ready summaries.

Generate multivariate color palettes to represent two-dimensional or three-dimensional data in graphics (in contrast to standard color palettes that represent just one variable). You tell colors3d how to map color space onto your data, and it gives you a color for each data point. You can then use these colors to make plots in base R', ggplot2', or other graphics frameworks.

Implementation of Hurst exponent estimators based on complex-valued lifting wavelet energy from Knight, M. I and Nunes, M. A. (2018) <doi:10.1007/s11222-018-9820-8>.

This package implements a class of univariate and multivariate spatial generalised linear mixed models for areal unit data, with inference in a Bayesian setting using Markov chain Monte Carlo (MCMC) simulation using a single or multiple Markov chains. The response variable can be binomial, Gaussian, multinomial, Poisson or zero-inflated Poisson (ZIP), and spatial autocorrelation is modelled by a set of random effects that are assigned a conditional autoregressive (CAR) prior distribution. A number of different models are available for univariate spatial data, including models with no random effects as well as random effects modelled by different types of CAR prior, including the BYM model (Besag et al., 1991, <doi:10.1007/BF00116466>) and Leroux model (Leroux et al., 2000, <doi:10.1007/978-1-4612-1284-3_4>). Additionally, a multivariate CAR (MCAR) model for multivariate spatial data is available, as is a two-level hierarchical model for modelling data relating to individuals within areas. Full details are given in the vignette accompanying this package. The initial creation of this package was supported by the Economic and Social Research Council (ESRC) grant RES-000-22-4256, and on-going development has been supported by the Engineering and Physical Science Research Council (EPSRC) grant EP/J017442/1, ESRC grant ES/K006460/1, Innovate UK / Natural Environment Research Council (NERC) grant NE/N007352/1 and the TB Alliance.

Searches for, accesses, and retrieves Statistics Canada data tables, as well as individual vectors, as tidy data frames. This package enriches the tables with metadata, deals with encoding issues, allows for bilingual English or French language data retrieval, and bundles convenience functions to make it easier to work with retrieved table data. For more efficient data access the package allows for caching data in a local database and database level filtering, data manipulation and summarizing.

Analyze and compare conversations using various similarity measures including topic, lexical, semantic, structural, stylistic, sentiment, participant, and timing similarities. Supports both pairwise conversation comparisons and analysis of multiple dyads. Methods are based on established research: Topic modeling: Blei et al. (2003) <doi:10.1162/jmlr.2003.3.4-5.993>; Landauer et al. (1998) <doi:10.1080/01638539809545028>; Lexical similarity: Jaccard (1912) <doi:10.1111/j.1469-8137.1912.tb05611.x>; Semantic similarity: Salton & Buckley (1988) <doi:10.1016/0306-4573(88)90021-0>; Mikolov et al. (2013) <doi:10.48550/arXiv.1301.3781>; Pennington et al. (2014) <doi:10.3115/v1/D14-1162>; Structural and stylistic analysis: Graesser et al. (2004) <doi:10.1075/target.21131.ryu>; Sentiment analysis: Rinker (2019) <https://github.com/trinker/sentimentr>.

This package provides functions for computing and visualizing generalized canonical discriminant analyses and canonical correlation analysis for a multivariate linear model. Traditional canonical discriminant analysis is restricted to a one-way MANOVA design and is equivalent to canonical correlation analysis between a set of quantitative response variables and a set of dummy variables coded from the factor variable. The candisc package generalizes this to higher-way MANOVA designs for all factors in a multivariate linear model, computing canonical scores and vectors for each term. The graphic functions provide low-rank (1D, 2D, 3D) visualizations of terms in an mlm via the plot.candisc and heplot.candisc methods. Related plots are now provided for canonical correlation analysis when all predictors are quantitative. Methods for linear discriminant analysis are now included.

The cito package provides a user-friendly interface for training and interpreting deep neural networks (DNN). cito simplifies the fitting of DNNs by supporting the familiar formula syntax, hyperparameter tuning under cross-validation, and helps to detect and handle convergence problems. DNNs can be trained on CPU, GPU and MacOS GPUs. In addition, cito has many downstream functionalities such as various explainable AI (xAI) metrics (e.g. variable importance, partial dependence plots, accumulated local effect plots, and effect estimates) to interpret trained DNNs. cito optionally provides confidence intervals (and p-values) for all xAI metrics and predictions. At the same time, cito is computationally efficient because it is based on the deep learning framework torch'. The torch package is native to R, so no Python installation or other API is required for this package.

This package contains functions to estimate the Correlation-Adjusted Regression Survival (CARS) Scores. The method is described in Welchowski, T. and Zuber, V. and Schmid, M., (2018), Correlation-Adjusted Regression Survival Scores for High-Dimensional Variable Selection, <arXiv:1802.08178>.