Model stability and variable inclusion plots [Mueller and Welsh (2010, <doi:10.1111/j.1751-5823.2010.00108.x>); Murray, Heritier and Mueller (2013, <doi:10.1002/sim.5855>)] as well as the adaptive fence [Jiang et al. (2008, <doi:10.1214/07-AOS517>); Jiang et al. (2009, <doi:10.1016/j.spl.2008.10.014>)] for linear and generalised linear models.

This package provides a modified function bic.glm of the BMA package that can be applied to multinomial logit (MNL) data. The data is converted to binary logit using the Begg & Gray approximation. The package also contains functions for maximum likelihood estimation of MNL.

Use standard genomics file format (BED) and a table of orthologs to illustrate synteny conservation at the genome-wide scale. Significantly conserved linkage groups are identified as described in Simakov et al. (2020) <doi:10.1038/s41559-020-1156-z> and displayed on an Oxford Grid (Edwards (1991) <doi:10.1111/j.1469-1809.1991.tb00394.x>) or a chord diagram as in Simakov et al. (2022) <doi:10.1126/sciadv.abi5884>. The package provides a function that uses a network-based greedy algorithm to find communities (Clauset et al. (2004) <doi:10.1103/PhysRevE.70.066111>) and so automatically order the chromosomes on the plot to improve interpretability.

Automated cell type annotation for single-cell RNA sequencing data using consensus predictions from multiple large language models. Integrates with Seurat objects and provides uncertainty quantification for annotations. Supports various LLM providers including OpenAI, Anthropic, and Google. For details see Yang et al. (2025) <doi:10.1101/2025.04.10.647852>.

This package implements FUSE (Functional Segmentation of DNA methylation data), a data-driven method for identifying spatially coherent DNA methylation segments from whole-genome bisulfite sequencing (WGBS) count data. The method performs hierarchical clustering of CpG sites based on methylated and unmethylated read counts across multiple samples and determines the optimal number of segments using an information criterion (AIC or BIC). Resulting segments represent regions with homogeneous methylation profiles across the input cohort while allowing sample-specific methylation levels. The package provides functions for clustering, model selection, tree cutting, segment-level summarization, and visualization. Input can be supplied as count matrices or extracted directly from BSseq and methrix objects.

This package provides common components (classes, methods, documentation) for packages that conduct meta-analytic corrections and sensitivity analyses for within-study and/or across-study biases in meta-analysis. See the packages PublicationBias', phacking', and multibiasmeta'. These package implement methods described in, respectively: Mathur & VanderWeele (2020) <doi:10.31219/osf.io/s9dp6>; Mathur (2022) <doi:10.31219/osf.io/ezjsx>; Mathur (2022) <doi:10.31219/osf.io/u7vcb>.

Leverages the R language to automate latent variable model estimation and interpretation using Mplus', a powerful latent variable modeling program developed by Muthen and Muthen (<https://www.statmodel.com>). Specifically, this package provides routines for creating related groups of models, running batches of models, and extracting and tabulating model parameters and fit statistics.

Computing transitive (and non-transitive) index numbers (Coelli et al., 2005 <doi:10.1007/b136381>) for cross-sections and panel data. For the calculation of transitive indexes, the EKS (Coelli et al., 2005 <doi:10.1007/b136381>; Rao et al., 2002 <doi:10.1007/978-1-4615-0851-9_4>) and Minimum spanning tree (Hill, 2004 <doi:10.1257/0002828043052178>) methods are implemented. Traditional fixed-base and chained indexes, and their growth rates, can also be derived using the Paasche, Laspeyres, Fisher and Tornqvist formulas.

Compute bootstrap confidence intervals for the adjusted Schnabel and Schumacher-Eschmeyer multi-visit mark-recapture estimators based on Dettloff (2023) <doi:10.1016/j.fishres.2023.106756>.

The MIDASim package is a microbiome data simulator for generating realistic microbiome datasets by adapting a user-provided template. It supports the controlled introduction of experimental signals-such as shifts in taxon relative abundances, prevalence, and sample library sizes-to create distinct synthetic populations under diverse simulation scenarios. For more details, see He et al. (2024) <doi:10.1186/s40168-024-01822-z>.

Multimodal mediation analysis is an emerging problem in microbiome data analysis. Multimedia make advanced mediation analysis techniques easy to use, ensuring that all statistical components are transparent and adaptable to specific problem contexts. The package provides a uniform interface to direct and indirect effect estimation, synthetic null hypothesis testing, bootstrap confidence interval construction, and sensitivity analysis. More details are available in Jiang et al. (2024) "multimedia: Multimodal Mediation Analysis of Microbiome Data" <doi:10.1101/2024.03.27.587024>.

The MetAlyzer S4 object provides methods to read and reformat metabolomics data for convenient data handling, statistics and downstream analysis. The resulting format corresponds to input data of the Shiny app MetaboExtract (<https://www.metaboextract.shiny.dkfz.de/MetaboExtract/>).

This package contains functions for performing Mokken scale analysis on test and questionnaire data. It includes an automated item selection algorithm, and various checks of model assumptions.

Estimates Variable Length Markov Chains (VLMC) models and VLMC with covariates models from discrete sequences. Supports model selection via information criteria and simulation of new sequences from an estimated model. See Bühlmann, P. and Wyner, A. J. (1999) <doi:10.1214/aos/1018031204> for VLMC and Zanin Zambom, A., Kim, S. and Lopes Garcia, N. (2022) <doi:10.1111/jtsa.12615> for VLMC with covariates.

Unbiased estimators of overall and per-class thematic map accuracy and area published in Olofsson et al. (2014) <doi:10.1016/j.rse.2014.02.015> and Stehman (2014) <doi:10.1080/01431161.2014.930207>.

This package provides functions, which make matrix creation conciser (such as the core package's function m() for rowwise matrix definition or runifm() for random value matrices). Allows to set multiple matrix values at once, by using list of formulae. Provides additional matrix operators and dedicated plotting function.

Normally building a GODB is fairly complicated, involving downloading multiple database files and using these to build e.g. a mySQL database. Accessing this database is also complicated, involving an intimate knowledge of the database in order to construct reliable queries. Here we have a more modest goal, generating GOGOA3, which is a stripped down version of the GODB that was originally restricted to human genes as designated by the HUGO Gene Nomenclature Committee (HGNC) (see <https://geneontology.org/>). I have now added about two dozen additional species, namely all species represented on the Gene Ontology download page <https://current.geneontology.org/products/pages/downloads.html>. This covers most of the model organisms that are commonly used in bio-medical and basic research (assuming that anyone still has a grant to do such research). This can be built in a matter of seconds from 2 easily downloaded files (see <https://current.geneontology.org/products/pages/downloads.html> and <https://geneontology.org/docs/download-ontology/>), and it can be queried by e.g. w<-which(GOGOA3[,"HGNC"] %in% hgncList) where GOGOA3 is a matrix representing the minimalist GODB and hgncList is a list of gene identifiers. This database will be used in my upcoming package GoMiner which is based on my previous publication (see Zeeberg, B.R., Feng, W., Wang, G. et al. (2003)<doi:10.1186/gb-2003-4-4-r28>). Relevant .RData files are available from GitHub (<https://github.com/barryzee/GO/tree/main/databases>).

This package implements the Maki (2012) <doi:10.1016/j.econmod.2012.05.006> cointegration test that allows for an unknown number of structural breaks. The test detects cointegration relationships in the presence of up to five structural breaks in the intercept and/or slope coefficients. Four different model specifications are supported: level shifts, level shifts with trend, regime shifts, and trend with regime shifts. The method is described in Maki (2012) "Tests for cointegration allowing for an unknown number of breaks" <doi:10.1016/j.econmod.2012.05.006>.

Overcomes one of the major challenges in mobile (passive) sensing, namely being able to pre-process the raw data that comes from a mobile sensing app, specifically m-Path Sense <https://m-path.io>. The main task of mpathsenser is therefore to read m-Path Sense JSON files into a database and provide several convenience functions to aid in data processing.

This package implements the algorithm of Remez (1962) for polynomial minimax approximation and of Cody et al. (1968) <doi:10.1007/BF02162506> for rational minimax approximation.

Enables us to use the functions of the package magick interactively.

Computes Monte Carlo standard errors for summaries of Monte Carlo output. Summaries and their standard errors are based on columns of Monte Carlo simulation output. Dennis D. Boos and Jason A. Osborne (2015) <doi:10.1111/insr.12087>.

Unsupervised learning has been widely used in many real-world applications. One of the simplest and most important unsupervised learning models is the Gaussian mixture model (GMM). In this work, we study the multi-task learning problem on GMMs, which aims to leverage potentially similar GMM parameter structures among tasks to obtain improved learning performance compared to single-task learning. We propose a multi-task GMM learning procedure based on the Expectation-Maximization (EM) algorithm that not only can effectively utilize unknown similarity between related tasks but is also robust against a fraction of outlier tasks from arbitrary sources. The proposed procedure is shown to achieve minimax optimal rate of convergence for both parameter estimation error and the excess mis-clustering error, in a wide range of regimes. Moreover, we generalize our approach to tackle the problem of transfer learning for GMMs, where similar theoretical results are derived. Finally, we demonstrate the effectiveness of our methods through simulations and a real data analysis. To the best of our knowledge, this is the first work studying multi-task and transfer learning on GMMs with theoretical guarantees. This package implements the algorithms proposed in Tian, Y., Weng, H., & Feng, Y. (2022) <arXiv:2209.15224>.

An S4 implementation of the unbiased extension of the model- assisted synthetic-regression estimator proposed by Mandallaz (2013) <DOI:10.1139/cjfr-2012-0381>, Mandallaz et al. (2013) <DOI:10.1139/cjfr-2013-0181> and Mandallaz (2014) <DOI:10.1139/cjfr-2013-0449>. It yields smaller variances than the standard bias correction, the generalised regression estimator.