model_comp

<code>model_comp</code> is a generic function that computes the model comparison measures (DIC and LPML) or the Pearson's residuals. Note that the Pearson's residuals are not available for <code>bayes.nmr</code> when <code>df</code> is either random or fixed but smaller than 2 since the variance of the random effects is not finite.

Contains functions performing Bayesian inference for meta-analytic and network meta-analytic models through Markov chain Monte Carlo algorithm. Currently, the package implements Hui Yao, Sungduk Kim, Ming-Hui Chen, Joseph G. Ibrahim, Arvind K. Shah, and Jianxin Lin (2015) <doi:10.1080/01621459.2015.1006065> and Hao Li, Daeyoung Lim, Ming-Hui Chen, Joseph G. Ibrahim, Sungduk Kim, Arvind K. Shah, Jianxin Lin (2021) <doi:10.1002/sim.8983>. For maximal computational efficiency, the Markov chain Monte Carlo samplers for each model, written in C++, are fine-tuned. This software has been developed under the auspices of the National Institutes of Health and Merck & Co., Inc., Kenilworth, NJ, USA.

Daeyoung Lim

metapack

Bayesian Meta-Analysis and Network Meta-Analysis

Ming-Hui Chen

Sungduk Kim

Joseph Ibrahim

Arvind Shah

Jianxin Lin

model_comp function

<dl><dt>object</dt>
<dd>the output model from fitting a meta analysis/regression model</dd>
<dt>type</dt>
<dd>the type of model comparison measure to compute; DIC or LPML</dd>
<dt>verbose</dt>
<dd>FALSE by default; If TRUE, then progress bar will appear</dd>
<dt>ncores</dt>
<dd>the number of CPU cores to use for parallel processing. It must not exceed the number of existing cores. If unspecified, it will default to 2 cores or the number of existing cores, whichever is smaller.</dd></dl>

Arguments

compute the model comparison measures: DIC, LPML, or Pearson's residuals — model_comp

<dl>

<dt>object</dt>
<dd>the output model from fitting a meta analysis/regression model</dd>


<dt>type</dt>
<dd>the type of model comparison measure to compute; DIC or LPML</dd>


<dt>verbose</dt>
<dd>FALSE by default; If TRUE, then progress bar will appear</dd>


<dt>ncores</dt>
<dd>the number of CPU cores to use for parallel processing. It must not exceed the number of existing cores. If unspecified, it will default to 2 cores or the number of existing cores, whichever is smaller.</dd>

</dl>

model_comp: compute the model comparison measures: DIC, LPML, or Pearson's residuals

Description

Usage

Value

Arguments