bayprior: bayprior: Bayesian Prior Elicitation for Clinical Trials

In bayprior: Bayesian Prior Elicitation and Diagnostics for Clinical Trials

bayprior: Bayesian Prior Elicitation for Clinical Trials

Description

A toolkit for constructing, validating, and justifying Bayesian priors in clinical trial settings. Implements SHELF-style expert elicitation (quantile matching, roulette method, moment matching) across six distribution families, linear and logarithmic expert pooling with compatibility validation, prior-data conflict diagnostics (Box p-value, surprise index, KL divergence, Bhattacharyya overlap, Mahalanobis check) for binary, continuous, Poisson/count, and survival data types, sensitivity analyses with tornado and influence plots, sceptical/robust/power priors, and automated HTML/PDF/Word regulatory reports informed by FDA and EMA guidance on Bayesian methods. Includes a fully modular Shiny application with automatic output reset on input change.

Main workflow

1. Elicitation – elicit_beta, elicit_normal, elicit_gamma, elicit_lognormal, elicit_exponential, elicit_weibull, elicit_roulette, elicit_mixture

2. Expert pooling – aggregate_experts

3. Conflict diagnostics – prior_conflict, conflict_mahalanobis

4. Sensitivity analysis – sensitivity_grid, sensitivity_cri

5. Robust priors – sceptical_prior, robust_prior, calibrate_power_prior

6. Reporting – prior_report

7. Shiny app – run_app

Distribution families

beta

Response rates and proportions – support (0, 1)

normal

Mean differences and log odds ratios – support (-Inf, Inf)

gamma

Event rates and median survival – support (0, Inf)

lognormal

Hazard ratios and PK parameters – support (0, Inf)

exponential

Constant hazard rates and Poisson rate priors – support (0, Inf). Conjugate with Poisson and survival data via Gamma-Poisson/Exponential updating.

weibull

Non-constant hazard survival times (OS, PFS) – support (0, Inf). Posterior approximated via Normal matching.

Data types for conflict diagnostics and sensitivity

"binary"

Events / sample size (x, n). Conjugate: Beta-Binomial.

"continuous"

Observed mean, SD, sample size (x, sd, n). Conjugate: Normal-Normal.

"poisson"

Event count / exposure person-time (x, n). Conjugate: Gamma-Poisson.

"survival"

Events / total follow-up time (x, n). Conjugate: Gamma-Exponential.

References

• O'Hagan et al. (2006). Uncertain Judgements. Wiley.

• Box (1980). JRSS-A, 143, 383–430.

• Schmidli et al. (2014). Biometrics, 70, 1023–1032.

• Ibrahim & Chen (2000). Statistical Science, 15, 46–60.

• Spiegelhalter et al. (1994). JRSS-A, 157, 357–416.

• FDA (2026). Use of Bayesian Methodology in Clinical Trials of Drug and Biological Products.

Author(s)

Maintainer: Ndoh Penn [e-mail]

See Also

Useful links:

• https://github.com/ndohpenngit/bayprior

• Report bugs at https://github.com/ndohpenngit/bayprior/issues

bayprior documentation built on Aug. 27, 2026, 1:09 a.m.