For a given test market find the best control markets using time series matching and analyze the impact of an intervention. The intervention could be a marketing event or some other local business tactic that is being tested. The workflow implemented in the Market Matching package utilizes dynamic time warping (the dtw package) to do the matching and the CausalImpact package to analyze the causal impact. In fact, this package can be considered a "workflow wrapper" for those two packages. In addition, if you don't have a chosen set of test markets to match, the Market Matching package can provide suggested test/control market pairs and pseudo prospective power analysis (measuring causal impact at fake interventions).

Following the common types of measures of uncertainty for parameter estimation, two measures of uncertainty were proposed for model selection, see Liu, Li and Jiang (2020) <doi:10.1007/s11749-020-00737-9>. The first measure is a kind of model confidence set that relates to the variation of model selection, called Mac. The second measure focuses on error of model selection, called LogP. They are all computed via bootstrapping. This package provides functions to compute these two measures. Furthermore, a similar model confidence set adapted from Bayesian Model Averaging can also be computed using this package.

Encodes several methods for performing Mendelian randomization analyses with summarized data. Similar to the MendelianRandomization package, but with fewer bells and whistles, and less frequent updates. As described in Yavorska (2017) <doi:10.1093/ije/dyx034> and Broadbent (2020) <doi:10.12688/wellcomeopenres.16374.2>.

Collect your data on digital marketing campaigns from Mailchimp using the Windsor.ai API <https://windsor.ai/api-fields/>.

This package provides a collection of helper functions for analyzing Second Primary Cancer data, including functions to reshape data, to calculate patient states and analyze cancer incidence.

Several robust estimators for linear regression and variable selection are provided. Included are Maximum tangent likelihood estimator by Qin, et al., (2017), arXiv preprint <doi:10.48550/arXiv.1708.05439>, least absolute deviance estimator and Huber regression. The penalized version of each of these estimator incorporates L1 penalty function, i.e., LASSO and Adaptive Lasso. They are able to produce consistent estimates for both fixed and high-dimensional settings.

This package provides functions for the creation, evaluation and test of decision models based in Multi Attribute Utility Theory (MAUT). Can process and evaluate local risk aversion utilities for a set of indexes, compute utilities and weights for the whole decision tree defining the decision model and simulate weights employing Dirichlet distributions under addition constraints in weights. Also includes other rating analysis methods as for example the Colley, Offensive - Defensive ratings and the ranking aggregation with Borda count.

Complements the book "Using R for Modelling and Quantitative Methods in Fisheries" ISBN 9780367469894, published in 2021 by Chapman & Hall in their "Using R series". There are numerous functions and data-sets that are used in the book's many practical examples.

Identifying important factors from a large number of potentially important factors of a highly nonlinear and computationally expensive black box model is a difficult problem. Xiao, Joseph, and Ray (2022) <doi:10.1080/00401706.2022.2141897> proposed Maximum One-Factor-at-a-Time (MOFAT) designs for doing this. A MOFAT design can be viewed as an improvement to the random one-factor-at-a-time (OFAT) design proposed by Morris (1991) <doi:10.1080/00401706.1991.10484804>. The improvement is achieved by exploiting the connection between Morris screening designs and Monte Carlo-based Sobol designs, and optimizing the design using a space-filling criterion. This work is supported by a U.S. National Science Foundation (NSF) grant CMMI-1921646 <https://www.nsf.gov/awardsearch/showAward?AWD_ID=1921646>.

Meta-analysis of generalized additive models and generalized additive mixed models. A typical use case is when data cannot be shared across locations, and an overall meta-analytic fit is sought. metagam provides functionality for removing individual participant data from models computed using the mgcv and gamm4 packages such that the model objects can be shared without exposing individual data. Furthermore, methods for meta-analysing these fits are provided. The implemented methods are described in Sorensen et al. (2020), <doi:10.1016/j.neuroimage.2020.117416>, extending previous works by Schwartz and Zanobetti (2000) and Crippa et al. (2018) <doi:10.6000/1929-6029.2018.07.02.1>.

Matching with string distance has never been easier! messy.cats contains various functions that employ string distance tools in order to make data management easier for users working with categorical data. Categorical data, especially user inputted categorical data that often tends to be plagued by typos, can be difficult to work with. messy.cats aims to provide functions that make cleaning categorical data simple and easy.

Convert Markdown ('.md') or R Markdown ('.Rmd') texts, R scripts, directory structures, and other hierarchical structured documents into mind map widgets or Freemind codes or Mermaid mind map codes, and vice versa. Freemind mind map ('.mm') files can be opened by or imported to common mind map software such as Freemind (<https://freemind.sourceforge.io/wiki/index.php/Main_Page>). Mermaid mind map codes (<https://mermaid.js.org/>) can be directly embedded in documents.

Split an untargeted metabolomics data set into a set of likely true metabolites and a set of likely measurement artifacts. This process involves comparing missing rates of pooled plasma samples and biological samples. The functions assume a fixed injection order of samples where biological samples are randomized and processed between intermittent pooled plasma samples. By comparing patterns of missing data across injection order, metabolites that appear in blocks and are likely artifacts can be separated from metabolites that seem to have random dispersion of missing data. The two main metrics used are: 1. the number of consecutive blocks of samples with present data and 2. the correlation of missing rates between biological samples and flanking pooled plasma samples.

Offers a gentle introduction to machine learning concepts for practitioners with a statistical pedigree: decomposition of model error (bias-variance trade-off), nonlinear correlations, information theory and functional permutation/bootstrap simulations. Székely GJ, Rizzo ML, Bakirov NK. (2007). <doi:10.1214/009053607000000505>. Reshef DN, Reshef YA, Finucane HK, Grossman SR, McVean G, Turnbaugh PJ, Lander ES, Mitzenmacher M, Sabeti PC. (2011). <doi:10.1126/science.1205438>.

This package provides real & simulated datasets containing time-series traffic observations and additional information pertaining to Loop 1 "Mopac" located in Austin, Texas.

This package provides methods for quality control and exploratory analysis of surface water quality data collected in Massachusetts, USA. Functions are developed to facilitate data formatting for the Water Quality Exchange Network <https://www.epa.gov/waterdata/water-quality-data-upload-wqx> and reporting of data quality objectives to state agencies. Quality control methods are from Massachusetts Department of Environmental Protection (2020) <https://www.mass.gov/orgs/massachusetts-department-of-environmental-protection>.

Implementations of an estimator for the multivariate regression association measure (MRAM) proposed in Shih and Chen (2026) <doi:10.1016/j.csda.2025.108288> and its associated variable selection algorithm. The MRAM quantifies the predictability of a random vector Y from a random vector X given a random vector Z. It takes the maximum value 1 if and only if Y is almost surely a measurable function of X and Z, and the minimum value of 0 if Y is conditionally independent of X given Z. The MRAM generalizes the Kendall's tau copula correlation ratio proposed in Shih and Emura (2021) <doi:10.1016/j.jmva.2020.104708> by employing the spatial sign function. The estimator is based on the nearest neighbor method, and the associated variable selection algorithm is adapted from the feature ordering by conditional independence (FOCI) algorithm of Azadkia and Chatterjee (2021) <doi:10.1214/21-AOS2073>. For further details, see the paper Shih and Chen (2026) <doi:10.1016/j.csda.2025.108288>.

This package provides pipe-style interface for data.table'. Package preserves all data.table features without significant impact on performance. let and take functions are simplified interfaces for most common data manipulation tasks. For example, you can write take(mtcars, mean(mpg), by = am) for aggregation or let(mtcars, hp_wt = hp/wt, hp_wt_mpg = hp_wt/mpg) for modification. Use take_if/let_if for conditional aggregation/modification. Additionally there are some conveniences such as automatic data.frame conversion to data.table'.

This package provides a suite of tools for transforming an existing workflow into a self-documenting pipeline with very minimal upfront costs. Segments of the pipeline are specified in much the same way a Make rule is, by declaring an executable recipe (which might be an R script), along with the corresponding targets and dependencies. When the entire pipeline is run through, only those recipes that need to be executed will be. Meanwhile, execution metadata is captured behind the scenes for later inspection.

This package provides a utility library to facilitate the generalization of statistical methods built on a regression framework. Package developers can use modelObj methods to initiate a regression analysis without concern for the details of the regression model and the method to be used to obtain parameter estimates. The specifics of the regression step are left to the user to define when calling the function. The user of a function developed within the modelObj framework creates as input a modelObj that contains the model and the R methods to be used to obtain parameter estimates and to obtain predictions. In this way, a user can easily go from linear to non-linear models within the same package.

Constructs genetic linkage maps in autopolyploid full-sib populations. Uses pairwise recombination fraction estimation as the first source of information to sequentially position allelic variants in specific homologous chromosomes. For situations where pairwise analysis has limited power, the algorithm relies on the multilocus likelihood obtained through a hidden Markov model (HMM). Methods are described in Mollinari and Garcia (2019) <doi:10.1534/g3.119.400378> and Mollinari et al. (2020) <doi:10.1534/g3.119.400620>.

Facilitate tasks typically encountered during metabolomics data analysis including data import, filtering, missing value imputation (Stacklies et al. (2007) <doi:10.1093/bioinformatics/btm069>, Stekhoven et al. (2012) <doi:10.1093/bioinformatics/btr597>, Tibshirani et al. (2017) <doi:10.18129/B9.BIOC.IMPUTE>, Troyanskaya et al. (2001) <doi:10.1093/bioinformatics/17.6.520>), normalization (Bolstad et al. (2003) <doi:10.1093/bioinformatics/19.2.185>, Dieterle et al. (2006) <doi:10.1021/ac051632c>, Zhao et al. (2020) <doi:10.1038/s41598-020-72664-6>) transformation, centering and scaling (Van Den Berg et al. (2006) <doi:10.1186/1471-2164-7-142>) as well as statistical tests and plotting. metamorphr introduces a tidy (Wickham et al. (2019) <doi:10.21105/joss.01686>) format for metabolomics data and is designed to make it easier to build elaborate analysis workflows and to integrate them with tidyverse packages including dplyr and ggplot2'.

Performance measures and scores for statistical classification such as accuracy, sensitivity, specificity, recall, similarity coefficients, AUC, GINI index, Brier score and many more. Calculation of optimal cut-offs and decision stumps (Iba and Langley (1991), <doi:10.1016/B978-1-55860-247-2.50035-8>) for all implemented performance measures. Hosmer-Lemeshow goodness of fit tests (Lemeshow and Hosmer (1982), <doi:10.1093/oxfordjournals.aje.a113284>; Hosmer et al (1997), <doi:10.1002/(SICI)1097-0258(19970515)16:9%3C965::AID-SIM509%3E3.0.CO;2-O>). Statistical and epidemiological risk measures such as relative risk, odds ratio, number needed to treat (Porta (2014), <doi:10.1093%2Facref%2F9780199976720.001.0001>).

Model based clustering using the multivariate multiple Scaled t (MST) and multivariate multiple scaled contaminated normal (MSCN) distributions. The MST is an extension of the multivariate Student-t distribution to include flexible tail behaviors, Forbes, F. & Wraith, D. (2014) <doi:10.1007/s11222-013-9414-4>. The MSCN represents a heavy-tailed generalization of the multivariate normal (MN) distribution to model elliptical contoured scatters in the presence of mild outliers (also referred to as "bad" points) and automatically detect bad points, Punzo, A. & Tortora, C. (2021) <doi:10.1177/1471082X19890935>.