Bayesian Model Averaging

Package for Bayesian model averaging and variable selection for linear models, generalized linear models and survival models (cox regression).

Bayesian Model Averaging for Random and Fixed Effects Meta-Analysis

Computes the posterior model probabilities for standard meta-analysis models (null model vs. alternative model assuming either fixed- or random-effects, respectively). These posterior probabilities are used to estimate the overall mean effect size as the weighted average of the mean effect size estimates of the random- and fixed-effect model as proposed by Gronau, Van Erp, Heck, Cesario, Jonas, & Wagenmakers (2017, ). The user can define a wide range of non-informative or informative priors for the mean effect size and the heterogeneity coefficient. Moreover, using pre-compiled Stan models, meta-analysis with continuous and discrete moderators with Jeffreys-Zellner-Siow (JZS) priors can be fitted and tested. This allows to compute Bayes factors and perform Bayesian model averaging across random- and fixed-effects meta-analysis with and without moderators. For a primer on Bayesian model-averaged meta-analysis, see Gronau, Heck, Berkhout, Haaf, & Wagenmakers (2021, ).

Bayesian Model Averaging Library

Bayesian Model Averaging for linear models with a wide choice of (customizable) priors. Built-in priors include coefficient priors (fixed, hyper-g and empirical priors), 5 kinds of model priors, moreover model sampling by enumeration or various MCMC approaches. Post-processing functions allow for inferring posterior inclusion and model probabilities, various moments, coefficient and predictive densities. Plotting functions available for posterior model size, MCMC convergence, predictive and coefficient densities, best models representation, BMA comparison. Also includes Bayesian normal-conjugate linear model with Zellner's g prior, and assorted methods.

Probabilistic Forecasting using Ensembles and Bayesian Model Averaging

Bayesian Model Averaging to create probabilistic forecasts from ensemble forecasts and weather observations < https://stat.uw.edu/sites/default/files/files/reports/2007/tr516.pdf>.

Bayesian Model Averaging with INLA

Fit Spatial Econometrics models using Bayesian model averaging on models fitted with INLA. The INLA package can be obtained from < https://www.r-inla.org>.

Bayesian Model Averaging for Basket Trials

An implementation of the Bayesian model averaging method of Psioda and others (2019) for basket trials. Contains a user-friendly wrapper for simulating basket trials under conditions and analyzing them with a Bayesian model averaging approach.

Free Knot-Bayesian Model Averaging

Analysis of Bayesian adaptive enrichment clinical trial using Free-Knot Bayesian Model Averaging (FK-BMA) method of Maleyeff et al. (2024) for Gaussian data. Maleyeff, L., Golchi, S., Moodie, E. E. M., & Hudson, M. (2024) "An adaptive enrichment design using Bayesian model averaging for selection and threshold-identification of predictive variables" .

A General Bayesian Model Averaging Helper

Provides helper functions to perform Bayesian model averaging using Markov chain Monte Carlo samples from separate models. Calculates weights and obtains draws from the model-averaged posterior for quantities of interest specified by the user. Weight calculations can be done using marginal likelihoods or log-predictive likelihoods as in Ando, T., & Tsay, R. (2010) .

Dose Response Models for Bayesian Model Averaging

Fits dose-response models utilizing a Bayesian model averaging approach as outlined in Gould (2019) for both continuous and binary responses. Longitudinal dose-response modeling is also supported in a Bayesian model averaging framework as outlined in Payne, Ray, and Thomann (2024) . Functions for plotting and calculating various posterior quantities (e.g. posterior mean, quantiles, probability of minimum efficacious dose, etc.) are also implemented. Copyright Eli Lilly and Company (2019).

Bayesian Model Averaging for Multinomial Logit Models

Provides a modified function bic.glm of the BMA package that can be applied to multinomial logit (MNL) data. The data is converted to binary logit using the Begg & Gray approximation. The package also contains functions for maximum likelihood estimation of MNL.