We are hiring ! See our job offers.
Raw File
Tip revision: 68a979e69aa2a1e57017730e1397470d5614d216 authored by Dominique Makowski on 02 September 2021, 23:10:30 UTC
version 0.11.0
Tip revision: 68a979e
% Generated by roxygen2: do not edit by hand
% Please edit documentation in R/unupdate.R
\title{Un-update Bayesian models to their prior-to-data state}
unupdate(model, verbose = TRUE, ...)

\method{unupdate}{stanreg}(model, verbose = TRUE, ...)

\method{unupdate}{brmsfit}(model, verbose = TRUE, ...)

\method{unupdate}{brmsfit_multiple}(model, verbose = TRUE, newdata = NULL, ...)

\method{unupdate}{blavaan}(model, verbose = TRUE, ...)
\item{model}{A fitted Bayesian model.}

\item{verbose}{Toggle warnings.}

\item{...}{Not used}

\item{newdata}{List of \code{data.frames} to update the model with new data. Required even if the original data should be used.}
A model un-fitted to the data, representing the prior model.
As posteriors are priors that have been updated after observing some data,
the goal of this function is to un-update the posteriors to obtain models
representing the priors. These models can then be used to examine the prior
predictive distribution, or to compare priors with posteriors.
This function in used internally to compute Bayes factors.
back to top