HGC (short for Hierarchical Graph-based Clustering) is an R package for conducting hierarchical clustering on large-scale single-cell RNA-seq (scRNA-seq) data. The key idea is to construct a dendrogram of cells on their shared nearest neighbor (SNN) graph. HGC provides functions for building graphs and for conducting hierarchical clustering on the graph. The users with old R version could visit https://github.com/XuegongLab/HGC/tree/HGC4oldRVersion to get HGC package built for R 3.6.

It provides functions to compute the values of different modifications of the Rand and Wallace indices. The indices are used to measure the stability or similarity of two partitions obtained on two different sets of units with a non-empty intercept. Splitting and merging of clusters can (depends on the selected index) have a different effect on the value of the indices. The indices are proposed in Cugmas and Ferligoj (2018) <http://ibmi.mf.uni-lj.si/mz/2018/no-1/Cugmas2018.pdf>.

This package contains functions for calculating the Federal Highway Administration (FHWA) Transportation Performance Management (TPM) performance measures. Currently, the package provides methods for the System Reliability and Freight (PM3) performance measures calculated from travel time data provided by The National Performance Management Research Data Set (NPMRDS), including Level of Travel Time Reliability (LOTTR), Truck Travel Time Reliability (TTTR), and Peak Hour Excessive Delay (PHED) metric scores for calculating statewide reliability performance measures. Implements <https://www.fhwa.dot.gov/tpm/guidance/pm3_hpms.pdf>.

Suite of tropical geometric tools for use in machine learning applications. These methods may be summarized in the following references: Yoshida, et al. (2022) <doi:10.2140/astat.2023.14.37>, Barnhill et al. (2023) <doi:10.48550/arXiv.2303.02539>, Barnhill and Yoshida (2023) <doi:10.3390/math11153433>, Aliatimis et al. (2023) <doi:10.1007/s11538-024-01327-8>, Yoshida et al. (2022) <doi:10.1109/TCBB.2024.3420815>, and Yoshida et al. (2019) <doi:10.1007/s11538-018-0493-4>.

This package provides a model for the growth of self-limiting populations using three, four, or five parameter functions, which have wide applications in a variety of fields. The dependent variable in a dynamical modeling could be the population size at time x, where x is the independent variable. In the analysis of quantitative polymerase chain reaction (qPCR), the dependent variable would be the fluorescence intensity and the independent variable the cycle number. This package then would calculate the TWW cycle threshold.

APL is a package developed for computation of Association Plots (AP), a method for visualization and analysis of single cell transcriptomics data. The main focus of APL is the identification of genes characteristic for individual clusters of cells from input data. The package performs correspondence analysis (CA) and allows to identify cluster-specific genes using Association Plots. Additionally, APL computes the cluster-specificity scores for all genes which allows to rank the genes by their specificity for a selected cell cluster of interest.

This package provides a testing framework for testing the multivariate point null hypothesis. A testing framework described in Elder et al. (2022) <arXiv:2203.01897> to test the multivariate point null hypothesis. After the user selects a parameter of interest and defines the assumed data generating mechanism, this information should be encoded in functions for the parameter estimator and its corresponding influence curve. Some parameter and data generating mechanism combinations have codings in this package, and are explained in detail in the article.

The Bayesian Federated Inference ('BFI') method combines inference results obtained from local data sets in the separate centers. In this version of the package, the BFI methodology is programmed for linear, logistic and survival regression models. For GLMs, see Jonker, Pazira and Coolen (2024) <doi:10.1002/sim.10072>; for survival models, see Pazira, Massa, Weijers, Coolen and Jonker (2024) <doi:10.48550/arXiv.2404.17464>; and for heterogeneous populations, see Jonker, Pazira and Coolen (2024) <doi:10.48550/arXiv.2402.02898>.

This code provides a method to fit the hidden compact representation model as well as to identify the causal direction on discrete data. We implement an effective solution to recover the above hidden compact representation under the likelihood framework. Please see the Causal Discovery from Discrete Data using Hidden Compact Representation from NIPS 2018 by Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang and Zhifeng Hao (2018) <https://nips.cc/Conferences/2018/Schedule?showEvent=11274> for a description of some of our methods.

Variable selection techniques are essential tools for model selection and estimation in high-dimensional statistical models. Through this publicly available package, we provide a unified environment to carry out variable selection using iterative sure independence screening (SIS) (Fan and Lv (2008)<doi:10.1111/j.1467-9868.2008.00674.x>) and all of its variants in generalized linear models (Fan and Song (2009)<doi:10.1214/10-AOS798>) and the Cox proportional hazards model (Fan, Feng and Wu (2010)<doi:10.1214/10-IMSCOLL606>).

Uniform Error Index is the weighted average of different error measures. Uniform Error Index utilizes output from different error function and gives more robust and stable error values. This package has been developed to compute Uniform Error Index from ten different loss function like Error Square, Square of Square Error, Quasi Likelihood Error, LogR-Square, Absolute Error, Absolute Square Error etc. The weights are determined using Principal Component Analysis (PCA) algorithm of Yeasin and Paul (2024) <doi:10.1007/s11227-023-05542-3>.

This package provides functions to assist in the processing and exploration of data from environmental monitoring programs. The package name stands for "water quality" and reflects the original focus on time series data for physical and chemical properties of water, as well as the biota. Intended for programs that sample approximately monthly, quarterly or annually at discrete stations, a feature of many legacy data sets. Most of the functions should be useful for analysis of similar-frequency time series regardless of the subject matter.

This LPE library is used to do significance analysis of microarray data with small number of replicates. It uses resampling based FDR adjustment, and gives less conservative results than traditional BH or BY procedures. Data accepted is raw data in txt format from MAS4, MAS5 or dChip. Data can also be supplied after normalization. LPE library is primarily used for analyzing data between two conditions. To use it for paired data, see LPEP library. For using LPE in multiple conditions, use HEM library.

R-dsb improves protein expression analysis in droplet-based single-cell studies. The package specifically addresses noise in raw protein UMI counts from methods like CITE-seq. It identifies and removes two main sources of noise—protein-specific noise from unbound antibodies and droplet/cell-specific noise. The package is applicable to various methods, including CITE-seq, REAP-seq, ASAP-seq, TEA-seq, and Mission Bioplatform data. Check the vignette for tutorials on integrating dsb with Seurat and Bioconductor, and using dsb in Python.

This package provides functions for demographic and epidemiological analysis in the Lexis diagram, i.e. register and cohort follow-up data, in particular representation, manipulation and simulation of multistate data - the Lexis suite of functions, which includes interfaces to the mstate, etm and cmprsk packages. It also contains functions for Age-Period-Cohort and Lee-Carter modeling and a function for interval censored data and some useful functions for tabulation and plotting, as well as a number of epidemiological data sets.

This package provides a new method for interpretable heterogeneous treatment effects characterization in terms of decision rules via an extensive exploration of heterogeneity patterns by an ensemble-of-trees approach, enforcing high stability in the discovery. It relies on a two-stage pseudo-outcome regression, and it is supported by theoretical convergence guarantees. Bargagli-Stoffi, F. J., Cadei, R., Lee, K., & Dominici, F. (2023) Causal rule ensemble: Interpretable Discovery and Inference of Heterogeneous Treatment Effects. arXiv preprint <doi:10.48550/arXiv.2009.09036>.

The development of ISM was made by Warfield in 1974. ISM is the process of collaborating distinct or related essentials into a simplified and an organized format. Hence, ISM is a methodology that seeks the interrelationships among the various elements considered and endows with a hierarchical and multilevel structure. To run this package user needs to provide a matrix (VAXO) converted into 0's and 1's. Warfield,J.N. (1974) <doi:10.1109/TSMC.1974.5408524> Warfield,J.N. (1974, E-ISSN:2168-2909).

The Joint Graphical Lasso is a generalized method for estimating Gaussian graphical models/ sparse inverse covariance matrices/ biological networks on multiple classes of data. We solve JGL under two penalty functions: The Fused Graphical Lasso (FGL), which employs a fused penalty to encourage inverse covariance matrices to be similar across classes, and the Group Graphical Lasso (GGL), which encourages similar network structure between classes. FGL is recommended over GGL for most applications. Reference: Danaher P, Wang P, Witten DM. (2013) <doi:10.1111/rssb.12033>.

Computes the implied weights of linear regression models for estimating average causal effects and provides diagnostics based on these weights. These diagnostics rely on the analyses in Chattopadhyay and Zubizarreta (2023) <doi:10.1093/biomet/asac058> where several regression estimators are represented as weighting estimators, in connection to inverse probability weighting. lmw provides tools to diagnose representativeness, balance, extrapolation, and influence for these models, clarifying the target population of inference. Tools are also available to simplify estimating treatment effects for specific target populations of interest.

This package provides a high level interface for torch providing utilities to reduce the the amount of code needed for common tasks, abstract away torch details and make the same code work on both the CPU and GPU'. It's flexible enough to support expressing a large range of models. It's heavily inspired by fastai by Howard et al. (2020) <arXiv:2002.04688>, Keras by Chollet et al. (2015) and PyTorch Lightning by Falcon et al. (2019) <doi:10.5281/zenodo.3828935>.

This package provides a facility to generate balanced semi-Latin rectangles with any cell size (preferably up to ten) with given number of treatments, see Uto, N.P. and Bailey, R.A. (2020). "Balanced Semi-Latin rectangles: properties, existence and constructions for block size two". Journal of Statistical Theory and Practice, 14(3), 1-11, <doi:10.1007/s42519-020-00118-3>. It also provides facility to generate partially balanced semi-Latin rectangles for cell size 2, 3 and 4 for any number of treatments.

Efficient Bayesian implementations of probit, logit, multinomial logit and binomial logit models. Functions for plotting and tabulating the estimation output are available as well. Estimation is based on Gibbs sampling where the Markov chain Monte Carlo algorithms are based on the latent variable representations and marginal data augmentation algorithms described in "Gregor Zens, Sylvia Frühwirth-Schnatter & Helga Wagner (2023). Ultimate Pólya Gamma Samplers â Efficient MCMC for possibly imbalanced binary and categorical data, Journal of the American Statistical Association <doi:10.1080/01621459.2023.2259030>".

This package provides a general toolkit for downloading, managing, analyzing, and presenting data from the U.S. Census, including SF1 (Decennial short-form), SF3 (Decennial long-form), and the American Community Survey (ACS). Confidence intervals provided with ACS data are converted to standard errors to be bundled with estimates in complex acs objects. The package provides new methods to conduct standard operations on acs objects and present/plot data in statistically appropriate ways.

This is an implementation of the Generalized Discrimination Score (also known as Two Alternatives Forced Choice Score, 2AFC) for various representations of forecasts and verifying observations. The Generalized Discrimination Score is a generic forecast verification framework which can be applied to any of the following verification contexts: dichotomous, polychotomous (ordinal and nominal), continuous, probabilistic, and ensemble. A comprehensive description of the Generalized Discrimination Score, including all equations used in this package, is provided by Mason and Weigel (2009) <doi:10.1175/MWR-D-10-05069.1>.