GUD - Bayesian Modal Regression Based on the GUD Family

Provides probability density functions and sampling algorithms for three key distributions from the General Unimodal Distribution (GUD) family: the Flexible Gumbel (FG) distribution, the Double Two-Piece (DTP) Student-t distribution, and the Two-Piece Scale (TPSC) Student-t distribution. Additionally, this package includes a function for Bayesian linear modal regression, leveraging these three distributions for model fitting. The details of the Bayesian modal regression model based on the GUD family can be found at Liu, Huang, and Bai (2024) <doi:10.1016/j.csda.2024.108012>.

Last updated

cpp

4.40 score 5 stars 2 scripts 131 downloads

MSIMST - Bayesian Monotonic Single-Index Regression Model with the Skew-T Likelihood

Incorporates a Bayesian monotonic single-index mixed-effect model with a multivariate skew-t likelihood, specifically designed to handle survey weights adjustments. Features include a simulation program and an associated Gibbs sampler for model estimation. The single-index function is constrained to be monotonic increasing, utilizing a customized Gaussian process prior for precise estimation. The model assumes random effects follow a canonical skew-t distribution, while residuals are represented by a multivariate Student-t distribution. Offers robust Bayesian adjustments to integrate survey weight information effectively.

Last updated

openblascpp

4.00 score 2 stars 147 downloads

DNNSIM - Single-Index Neural Network for Skewed Heavy-Tailed Data

Provides a deep neural network model with a monotonic increasing single index function tailored for periodontal disease studies. The residuals are assumed to follow a skewed T distribution, a skewed normal distribution, or a normal distribution. More details can be found at Liu, Huang, and Bai (2024) <doi:10.1016/j.csda.2024.108012>.

Last updated

2.70 score 1 stars 131 downloads

BayesPocket - Bayesian Causal Inference for Periodontal Diseases in Longitudinal Studies

Implements the Mixed Treatment-State Causal Model (MTSCM), a Bayesian framework for estimating causal effects of clinical interventions on bounded continuous outcomes in longitudinal observational studies with irregular visits. The methodology is specifically designed for periodontal disease research, where discrete treatments and continuous disease states (e.g., proportion of periodontal pockets exceeding 3 mm) reciprocally influence one another under dynamic feedback. The package integrates a double-censored Tobit likelihood to handle boundary mass at zero and one, subject-specific random effects to capture within-subject correlation, and flexible tree-based ensemble priors (standard BART and Soft BART) to model complex nonlinear interactions without parametric restrictions. Causal identification is established under the potential outcomes framework via the G-computation formula, with key estimands including the Mixed Average Potential Outcome (MAPO) and the Mixed Probability of Disease Resolution (MPDR). The package provides functions for model fitting, posterior inference, and causal estimand estimation.

Last updated

1.00 score

BayesPocket - Bayesian Causal Inference for Periodontal Diseases in Longitudinal Studies

Implements the Mixed Treatment-State Causal Model (MTSCM), a Bayesian framework for estimating causal effects of clinical interventions on bounded continuous outcomes in longitudinal observational studies with irregular visits. The methodology is specifically designed for periodontal disease research, where discrete treatments and continuous disease states (e.g., proportion of periodontal pockets exceeding 3 mm) reciprocally influence one another under dynamic feedback. The package integrates a double-censored Tobit likelihood to handle boundary mass at zero and one, subject-specific random effects to capture within-subject correlation, and flexible tree-based ensemble priors (standard BART and Soft BART) to model complex nonlinear interactions without parametric restrictions. Causal identification is established under the potential outcomes framework via the G-computation formula, with key estimands including the Mixed Average Potential Outcome (MAPO) and the Mixed Probability of Disease Resolution (MPDR). The package provides functions for model fitting, posterior inference, and causal estimand estimation.

Last updated

1.00 score

BAREB - A Bayesian Repulsive Biclustering Model for Periodontal Data

Simultaneously clusters the Periodontal diseases (PD) patients and their tooth sites after taking the patient- and site-level covariates into consideration. 'BAREB' uses the determinantal point process (DPP) prior to induce diversity among different biclusters to facilitate parsimony and interpretability. Essentially, 'BAREB' is a cluster-wise linear model based on Yuliang (2020) <doi:10.1002/sim.8536>.

Last updated

openblascppopenmp

1.00 score 3 scripts 203 downloads