Approximate marginal maximum likelihood estimation of multidimensional latent variable models via adaptive quadrature or Laplace approximations to the integrals in the likelihood function, as presented for confirmatory factor analysis models in Jin, S., Noh, M., and Lee, Y. (2018) <doi:10.1080/10705511.2017.1403287>, for item response theory models in Andersson, B., and Xin, T. (2021) <doi:10.3102/1076998620945199>, and for generalized linear latent variable models in Andersson, B., Jin, S., and Zhang, M. (2023) <doi:10.1016/j.csda.2023.107710>. Models implemented include the generalized partial credit model, the graded response model, and generalized linear latent variable models for Poisson, negative-binomial and normal distributions. Supports a combination of binary, ordinal, count and continuous observed variables and multiple group models.

"Learning with Subset Stacking" is a supervised learning algorithm that is based on training many local estimators on subsets of a given dataset, and then passing their predictions to a global estimator. You can find the details about LESS in our manuscript at <arXiv:2112.06251>.

Hidden Markov Model (HMM) based on symmetric lambda distribution framework is implemented for the study of return time-series in the financial market. Major features in the S&P500 index, such as regime identification, volatility clustering, and anti-correlation between return and volatility, can be extracted from HMM cleanly. Univariate symmetric lambda distribution is essentially a location-scale family of exponential power distribution. Such distribution is suitable for describing highly leptokurtic time series obtained from the financial market. It provides a theoretically solid foundation to explore such data where the normal distribution is not adequate. The HMM implementation follows closely the book: "Hidden Markov Models for Time Series", by Zucchini, MacDonald, Langrock (2016).

This package performs likelihood-based inference for stationary time series extremes. The general approach follows Fawcett and Walshaw (2012) <doi:10.1002/env.2133>. Marginal extreme value inferences are adjusted for cluster dependence in the data using the methodology in Chandler and Bate (2007) <doi:10.1093/biomet/asm015>, producing an adjusted log-likelihood for the model parameters. A log-likelihood for the extremal index is produced using the K-gaps model of Suveges and Davison (2010) <doi:10.1214/09-AOAS292>. These log-likelihoods are combined to make inferences about extreme values. Both maximum likelihood and Bayesian approaches are available.

User-friendly and generalized tools for the calculation of luck -- moments of variation in metrics like lifespan and lifetime reproductive output. We provide tools for calculating those moments and also performing decompositions into contributions from, for example, individual traits, environmental impacts, and luck (also called individual stochasticity). The functions included here are based on Snyder and Ellner (2024) <doi:10.1086/730557>, Cochran and Ellner (1992) <https://www.jstor.org/stable/2937115>, and Hernandez et al. (2024) <doi:10.1111/ele.14390>.

This package provides a Low Rank Correction Variational Bayesian algorithm for high-dimensional multi-source heterogeneous quantile linear models. More details have been written up in a paper submitted to the journal Statistics in Medicine, and the details of variational Bayesian methods can be found in Ray and Szabo (2021) <doi:10.1080/01621459.2020.1847121>. It simultaneously performs parameter estimation and variable selection. The algorithm supports two model settings: (1) local models, where variable selection is only applied to homogeneous coefficients, and (2) global models, where variable selection is also performed on heterogeneous coefficients. Two forms of parameter estimation are output: one is the standard variational Bayesian estimation, and the other is the variational Bayesian estimation corrected with low-rank adjustment.

Convenient aliases for common ways of misspelling the base R function length(). These include every permutation of the final three letters.

Simplify the loading matrix in factor models using the l1 criterion as proposed in Freyaldenhoven (2025) <doi:10.21799/frbp.wp.2020.25>. Given a data matrix, find the rotation of the loading matrix with the smallest l1-norm and/or test for the presence of local factors with main function local_factors().

Estimation of Latent Order Logistic (LOLOG) Models for Networks. LOLOGs are a flexible and fully general class of statistical graph models. This package provides functions for performing MOM, GMM and variational inference. Visual diagnostics and goodness of fit metrics are provided. See Fellows (2018) <doi:10.48550/arXiv.1804.04583> for a detailed description of the methods.

Under an L0 penalty framework, a computationally efficient implementation of change point detection is developed. By integrating active set algorithms with warm start initialization, the package achieves linear-time complexity for solving change point detection problems. References: Wen et al. (2020) <doi:10.18637/jss.v094.i04>; Zhu et al. (2020)<doi:10.1073/pnas.2014241117>.

Logger to keep track of informational events and errors useful for debugging.

Access to the Greek New Testament (27 books) and the Old Testament (39 books) and allow users to do textual analysis on the data. The New and Old Testament have been provided in their original languages, Greek and Hebrew, respectively. Additionally, the Revised American Standard Bible is also provided for users who'd rather use a wordâ forâ word modern English translation.

Cellular cooperation compromises the established method of calculating clonogenic activity from limiting dilution assay (LDA) data. This tool provides functions that enable robust analysis in presence or absence of cellular cooperation. The implemented method incorporates the same cooperativity module to model the non-linearity associated with cellular cooperation as known from the colony formation assay (Brix et al. (2021) <doi:10.1038/s41596-021-00615-0>: "Analysis of clonogenic growth in vitro." Nature protocols).

This package provides tools for estimation and inference of conditional densities, derivatives and functions. This is the companion software for Cattaneo, Chandak, Jansson and Ma (2024) <doi:10.3150/23-BEJ1711>.

Computes the Lomb-Scargle Periodogram and actogram for evenly or unevenly sampled time series. Includes a randomization procedure to obtain exact p-values. Partially based on C original by Press et al. (Numerical Recipes) and the Python module Astropy. For more information see Ruf, T. (1999). The Lomb-Scargle periodogram in biological rhythm research: analysis of incomplete and unequally spaced time-series. Biological Rhythm Research, 30(2), 178-201.

Calculate point estimates of and valid confidence intervals for longitudinal summaries of nonparametric, algorithm-agnostic variable importance measures. For more details, see Williamson et al. (2024) <doi:10.48550/arXiv.2311.01638>.

The Programme for International Student Assessment (PISA) is a global study conducted by the Organization for Economic Cooperation and Development (OECD) in member and non-member countries to assess educational systems by assessing 15-year-old school students academic performance in mathematics, science, and reading. This datasets contains information on their scores and other socioeconomic characteristics, information about their school and its infrastructure, as well as the countries that are taking part in the program.

Create small multiples of several leaflet web maps with (optional) synchronised panning and zooming control. When syncing is enabled all maps respond to mouse actions on one map. This allows side-by-side comparisons of different attributes of the same geometries. Syncing can be adjusted so that any combination of maps can be synchronised.

The package compiles functions for calculating prices of American put options with Least Squares Monte Carlo method. The option types are plain vanilla American put, Asian American put, and Quanto American put. The pricing algorithms include variance reduction techniques such as Antithetic Variates and Control Variates. Additional functions are given to derive "price surfaces" at different volatilities and strikes, create 3-D plots, quickly generate Geometric Brownian motion, and calculate prices of European options with Black & Scholes analytical solution.

Non-parametric estimators for casual effects based on longitudinal modified treatment policies as described in Diaz, Williams, Hoffman, and Schenck <doi:10.1080/01621459.2021.1955691>, traditional point treatment, and traditional longitudinal effects. Continuous, binary, categorical treatments, and multivariate treatments are allowed as well are censored outcomes. The treatment mechanism is estimated via a density ratio classification procedure irrespective of treatment variable type. For both continuous and binary outcomes, additive treatment effects can be calculated and relative risks and odds ratios may be calculated for binary outcomes. Supports survival outcomes with competing risks (Diaz, Hoffman, and Hejazi; <doi:10.1007/s10985-023-09606-7>).

This package implements the kK-NN algorithm, an adaptive k-nearest neighbor classifier that adjusts the neighborhood size based on local data curvature. The method estimates local Gaussian curvature by approximating the shape operator of the data manifold. This approach aims to improve classification performance, particularly in datasets with limited samples.

This package provides a LaTeX Letter class for rmarkdown', using the pandoc-letter template adapted for use with markdown'.

Computing statistical hypothesis testing for loading in principal component analysis (PCA) (Yamamoto, H. et al. (2014) <doi:10.1186/1471-2105-15-51>), orthogonal smoothed PCA (OS-PCA) (Yamamoto, H. et al. (2021) <doi:10.3390/metabo11030149>), one-sided kernel PCA (Yamamoto, H. (2023) <doi:10.51094/jxiv.262>), partial least squares (PLS) and PLS discriminant analysis (PLS-DA) (Yamamoto, H. et al. (2009) <doi:10.1016/j.chemolab.2009.05.006>), PLS with rank order of groups (PLS-ROG) (Yamamoto, H. (2017) <doi:10.1002/cem.2883>), regularized canonical correlation analysis discriminant analysis (RCCA-DA) (Yamamoto, H. et al. (2008) <doi:10.1016/j.bej.2007.12.009>), multiset PLS and PLS-ROG (Yamamoto, H. (2022) <doi:10.1101/2022.08.30.505949>).

Generates the Langa-Weir classification of cognitive function for the 2022 Health and Retirement Study (HRS) cognition data. It is particularly useful for researchers studying cognitive aging who wish to work with the most recent release of HRS data. The package provides user-friendly functions for data preprocessing, scoring, and classification allowing users to easily apply the Langa-Weir classification system. For details regarding the; HRS <https://hrsdata.isr.umich.edu/> and Langa-Weir classifications <https://hrsdata.isr.umich.edu/data-products/langa-weir-classification-cognitive-function-1995-2020>.