Learn R Programming

BayesFBHborrow (version 2.0.2)

Bayesian Dynamic Borrowing with Flexible Baseline Hazard Function

Description

Allows Bayesian borrowing from a historical dataset for time-to- event data. A flexible baseline hazard function is achieved via a piecewise exponential likelihood with time varying split points and smoothing prior on the historic baseline hazards. The method is described in Scott and Lewin (2024) , and the software paper is in Axillus et al. (2024) .

Copy Link

Version

Install

install.packages('BayesFBHborrow')

Monthly Downloads

198

Version

2.0.2

License

Apache License (>= 2)

Maintainer

Darren Scott

Last Published

September 16th, 2024

Functions in BayesFBHborrow (2.0.2)

GibbsMH.NoBorrow

GibbsMH sampler, without Bayesian Borrowing

GibbsMH.WBorrow

GibbsMH sampler, with Bayesian Borrowing

BayesFBHborrow: Run MCMC for a piecewise exponential model

.J_RJMCMC_NoBorrow

RJMCMC (without Bayesian Borrowing)

BayesFBHborrow.WBorrow

Run the MCMC sampler with Bayesian Borrowing

RJMCMC (with Bayesian Borrowing)

Calculate covariance matrix in the MVN-ICAR

S3 generic, calls the correct GibbsMH sampler

coef.BayesFBHborrow

Extract mean posterior values

BayesFBHborrow.NoBorrow

Run the MCMC sampler without Bayesian Borrowing

Proposal beta with a Metropolis Adjusted Langevin (MALA)

Beta Metropolis-Hastings random walk move

Newton Raphson MH move

Create data.frame for piecewise exponential models

Calculate log density tau prior

.lambda_0_MH_cp

Lambda_0 MH step, proposal from conditional conjugate posterior

Mean for MALA using derivative for beta proposal

.beta_mom.NR.fun

First and second derivative of target for mode and variance of proposal

.beta.MH.RW.glm

Beta MH RW sampler from freq PEM fit

Birth move in RJMCMC

Calculate mu posterior update

.lprop.dens.beta.NR

log Gaussian proposal density for Newton Raphson proposal

Calculate log gamma ratio for two different parameter values

.lprop_density_beta

Log density of proposal for MALA

.llikelihood_ratio_lambda

Log likelihood for lambda / lambda_0 update

.shuffle_split_point_location

Metropolis Hastings step: shuffle the split point locations (with Bayesian borrowing)

.lambda_conj_prop

Propose lambda from a gamma conditional conjugate posterior proposal

.llikelihood_ratio_beta

Loglikelihood ratio calculation for beta parameters

.log_likelihood

Log likelihood function

Plot histogram from MCMC samples

.nu_sigma_update

Calculates nu and sigma2 for the Gaussian Markov random field prior, for a given split point j

Death move in RJMCMC

Computes the logarithmic sum of an exponential

.normalize_prob

Normalize a set of probability to one, using the the log-sum-exp trick

Plot smoothed baseline hazards

.predictive_survival

Predictive survival from BayesFBHborrow object

.set_tuning_parameters

Set tuning parameters

summary.BayesFBHborrow

Summarize fixed MCMC results

piecewise_exp_cc

Example data, simulated from a piecewise exponential model.

.set_hyperparameters

Set tuning parameters

Smoothed hazard function

.predictive_hazard_ratio

Predictive hazard ratio (HR) from BayesFBHborrow object

Calculate sigma2 posterior update

plot.BayesFBHborrow

Plot the MCMC results

.shuffle_split_point_location_NoBorrow

Metropolis Hastings step: shuffle the split point locations (without Bayesian borrowing)

piecewise_exp_hist

Example data, simulated from a piecewise exponential model.

Example data, simulated from a Weibull distribution.

Example data, simulated from a Weibull distribution

Fit frequentist piecewise exponential model for MLE and information matrix of beta

.lambda_0_MH_cp_NoBorrow

Lambda_0 MH step, proposal from conditional conjugate posterior

Lambda MH step, proposal from conditional conjugate posterior

Create group level data

init_lambda_hyperparameters

Initialize lambda hyperparameters

Plot MCMC trace

.predictive_hazard

Predictive hazard from BayesFBHborrow object

.smooth_survival

Smoothed survival curve

Sample tau from posterior distribution