No packages match

summary2joint - Joint Distribution Estimation from Marginal Study Summaries

Estimates latent Gaussian joint distributions for normal continuous, binary, and ordinal variables using marginal summaries from independent studies of a common population. Fits a pairwise Gaussian working criterion using exact summary moments, with study-level sandwich uncertainty. Supports prespecified independent groups, joint event probabilities, and synthetic patient generation. Identification requires repeated joint reporting of variable pairs; heterogeneous populations, rare categories, and small study collections require caution.

Last updated

openblascpp

2.70 score

mvboxcox - Bivariate Logistic Box-Cox Regression

Fits bivariate logistic Box-Cox regression models for binary outcomes and positive continuous predictors. Transformation parameters are selected by cross-validated grid search with adaptive refinement and thin-plate spline smoothing. The package also provides prediction, empirical and sampling-weighted median effects, simulation tools, and sampling-weighted model fitting. The methodology extends the logistic Box-Cox approach of Xing et al. (2021) <doi:10.1002/cjs.11587>.

Last updated

2.70 score 272 downloads

bin2norm - Hierarchical Probit Estimation for Dichotomized Data

Provides likelihood-based and hierarchical estimation methods for thresholded (binomial-probit) data. Supports fixed-mean and random-mean models with maximum likelihood estimation (MLE), generalized linear mixed model (GLMM), and Bayesian Markov chain Monte Carlo (MCMC) implementations. For methodological background, see Albert and Chib (1993) <doi:10.1080/01621459.1993.10476321> and McCulloch (1994) <doi:10.2307/2297959>.

Last updated

2.00 score 343 downloads

iimi - Identifying Infection with Machine Intelligence

A novel machine learning method for plant viruses diagnostic using genome sequencing data. This package includes three different machine learning models, random forest, XGBoost, and elastic net, to train and predict mapped genome samples. Mappability profile and unreliable regions are introduced to the algorithm, and users can build a mappability profile from scratch with functions included in the package. Plotting mapped sample coverage information is provided.

Last updated

2.00 score 7 scripts 363 downloads

ebdm - Estimating Bivariate Dependency from Marginal Data

Provides statistical methods for estimating bivariate dependency (correlation) from marginal summary statistics across multiple studies. The package supports three modules of bivariate joint distribution estimated from marginal summary data: (1) two binary, (2) two continuous, (3) one binary and one continuous These methods enable privacy-preserving joint estimation when individual-level data are unavailable. The approaches are detailed in Shang, Tsao, and Zhang (2025a) <doi:10.48550/arXiv.2505.03995> and Shang, Tsao, and Zhang (2025b) <doi:10.48550/arXiv.2508.02057>.

Last updated

1.30 score 2 scripts 259 downloads

glmpermu - Permutation-Based Inference for Generalized Linear Models

In practical applications, the assumptions underlying generalized linear models frequently face violations, including incorrect specifications of the outcome variable's distribution or omitted predictors. These deviations can render the results of standard generalized linear models unreliable. As the sample size increases, what might initially appear as minor issues can escalate to critical concerns. To address these challenges, we adopt a permutation-based inference method tailored for generalized linear models. This approach offers robust estimations that effectively counteract the mentioned problems, and its effectiveness remains consistent regardless of the sample size.

Last updated

1.00 score 167 downloads

bossR - Biomarker Optimal Segmentation System

The Biomarker Optimal Segmentation System R package, 'bossR', is designed for precision medicine, helping to identify individual traits using biomarkers. It focuses on determining the most effective cutoff value for a continuous biomarker, which is crucial for categorizing patients into two groups with distinctly different clinical outcomes. The package simultaneously finds the optimal cutoff from given candidate values and tests its significance. Simulation studies demonstrate that 'bossR' offers statistical power and false positive control non-inferior to the permutation approach (considered the gold standard in this field), while being hundreds of times faster.

Last updated

1.00 score 227 downloads