stackMI

formula

fitter

an object created by <code>transcan</code>, <code><a rd-options="" href="/link/aregImpute?package=rms&version=6.0-0" data-mini-rdoc="rms::aregImpute">aregImpute</a></code>, or <code><a rd-options="mice" href="/link/mice?package=rms&version=6.0-0&to=mice" data-mini-rdoc="mice::mice">mice</a></code>

xtrans

data

number of imputations to run, default is the number saved in <code>xtrans</code>

n.impute

see <code>Hmisc::fit.mult.impute</code>

dtrans

derived

an integer or logical vector specifying the subset of observations to fit

subset

see [rstan::sampling]. The default is 0, indicating that no progress notes are output. If <code>refresh &gt; 0</code> and <code>progress</code> is not <code>''</code>, progress output will be appended to file <code>progress</code>. The default file name is <code>'stan-progress.txt'</code>.

refresh

see <code>refresh</code>. Defaults to <code>''</code> if <code>refresh = 0</code>. Note: If running interactively but not under RStudio, <code>rstan</code> will open a browser window for monitoring progress.

progress

arguments passed to <code>fitter</code>

Runs an <code>rms</code> package Bayesian fitting function such as <code>blrm</code> separately for each completed dataset given a multiple imputation result such as one produced by <code>Hmisc::aregImpute</code>. Stacks the posterior draws and diagnostics across all imputations, and computes parameter summaries on the stacked posterior draws.
stackMI

Regression modeling, testing, estimation, validation,
graphics, prediction, and typesetting by storing enhanced model design
attributes in the fit.  'rms' is a collection of functions that
assist with and streamline modeling.  It also contains functions for
binary and ordinal logistic regression models, ordinal models for
continuous Y with a variety of distribution families, and the Buckley-James
multiple regression model for right-censored responses, and implements
penalized maximum likelihood estimation for logistic and ordinary
linear models.  'rms' works with almost any regression model, but it
was especially written to work with binary or ordinal regression
models, Cox regression, accelerated failure time models,
ordinary linear models,	the Buckley-James model, generalized least
squares for serially or spatially correlated observations, generalized
linear models, and quantile regression.  Bayesian methods are implemented for binary and ordinal logistic regression with or without random effects.

Frank E Harrell Jr

Regression Modeling Strategies

stackMI function

an object created by <code>transcan</code>, <code><a rd-options='' href='aregImpute'>aregImpute</a></code>, or <code><a rd-options='mice' href='mice'>mice</a></code>

stackMI: Bayesian Model Fitting and Stacking for Multiple Imputation

Description

Usage

Arguments

Value