traceplot

traceplot,stanfit-method

An instance of class <code><a href="/link/?package=rstan&version=2.15.1" data-mini-rdoc="rstan::"></a></code>.

object

A character vector of parameter names. Defaults to all parameters 
    or the first 10 parameters (if there are more than 10).

pars

Should the parameters given by the <code>pars</code> argument be
    included (the default) or excluded from the plot? Only relevant if 
    <code>pars</code> is not missing.

include

<code>TRUE</code> or <code>FALSE</code>, indicating whether 
    the warmup sample are included in the trace plot; defaults to <code>FALSE</code>.

inc_warmup

A vector of length 2. Iterations between <code>window[1]</code>
    and <code>window[2]</code> will be shown in the plot. The default is to 
    show all iterations if <code>inc_warmup</code> is <code>TRUE</code> and all iterations
    from the sampling period only if <code>inc_warmup</code> is <code>FALSE</code>. If 
    <code>inc_warmup</code> is <code>FALSE</code> the iterations specified in <code>window</code>
    should not include iterations from the warmup period.

window

Should parameters be plotted on the unconstrained space?
    Defaults to <code>FALSE</code>.

unconstrain

Passed to <code><a rd-options="ggplot2" href="/link/facet_wrap?package=rstan&version=2.15.1&to=ggplot2" data-mini-rdoc="ggplot2::facet_wrap">facet_wrap</a></code>.

nrow,ncol

Optional arguments to pass to <code><a rd-options="ggplot2" href="/link/geom_path?package=rstan&version=2.15.1&to=ggplot2" data-mini-rdoc="ggplot2::geom_path">geom_path</a></code> 
    (e.g. <code>size</code>, <code>linetype</code>, <code>alpha</code>, etc.).

&#8230;

Draw the traceplot corresponding to one or more
 Markov chains, providing a visual way to inspect sampling behavior
 and assess mixing across chains and convergence.

methods

User-facing R functions are provided to parse, compile, test,
estimate, and analyze Stan models by accessing the header-only Stan library
provided by the 'StanHeaders' package. The Stan project develops a
probabilistic programming language that implements full Bayesian statistical
inference via Markov Chain Monte Carlo, rough Bayesian inference via 'variational'
approximation, and (optionally penalized) maximum likelihood estimation via
optimization. In all three cases, automatic differentiation is used to quickly
and accurately evaluate gradients without burdening the user with the need
to derive the partial derivatives.

Ben Goodrich

rstan

R Interface to Stan

Jiqiang Guo

Jonah Gabry

Daniel Lee

Krzysztof Sakrejda

Trustees of Columbia University

Oleg Sklyar

The R Core Team

Jens Oehlschlaegel-Akiyoshi

Hadley Wickham

Joel de Guzman

John Fletcher

Thomas Heller

Eric Niebler

traceplot function

<dl class="dl-horizontal">
    <dt>traceplot</dt><dd><code>signature(object = &quot;stanfit&quot;)</code></dd>Plot the sampling paths for all chains.
  </dl>

Methods

An instance of class <code><a href='stanfit'></a></code>.

Passed to <code><a rd-options='ggplot2' href='facet_wrap'>facet_wrap</a></code>.

Optional arguments to pass to <code><a rd-options='ggplot2' href='geom_path'>geom_path</a></code> 
    (e.g. <code>size</code>, <code>linetype</code>, <code>alpha</code>, etc.).

Markov chain traceplots — traceplot

<dl class='dl-horizontal'>
    <dt>traceplot</dt><dd><code>signature(object = &quot;stanfit&quot;)</code></dd>Plot the sampling paths for all chains.
  </dl>

traceplot: Markov chain traceplots

Description

Usage

Arguments

Value

Methods

See Also

Examples