print.loo

A list with class <code>'loo'</code> (as returned by <code><a rd-options="" href="/link/loo?package=loo&version=1.0.0" data-mini-rdoc="loo::loo">loo</a></code> or
<code><a rd-options="" href="/link/waic?package=loo&version=1.0.0" data-mini-rdoc="loo::waic">waic</a></code>).

An integer passed to <code><a rd-options="base" href="/link/round?package=loo&version=1.0.0&to=base" data-mini-rdoc="base::round">round</a></code>.

digits

Logical. If <code>TRUE</code> the estimates of the Pareto shape
parameter $k$ are plotted. Ignored if <code>x</code> was generated by
<code><a rd-options="" href="/link/waic?package=loo&version=1.0.0" data-mini-rdoc="loo::waic">waic</a></code>. To just plot $k$ without printing use the
<code><a rd-options="=pareto-k-diagnostic" href="/link/plot%20method?package=loo&version=1.0.0&to=%3Dpareto-k-diagnostic" data-mini-rdoc="=pareto-k-diagnostic::plot method">plot method</a></code>.

plot_k

Arguments passed to <code><a rd-options="" href="/link/plot.loo?package=loo&version=1.0.0" data-mini-rdoc="loo::plot.loo">plot.loo</a></code> if <code>plot_k</code> is
<code>TRUE</code>.

Efficient approximate leave-one-out cross-validation (LOO)
using Pareto smoothed importance sampling (PSIS), a new procedure for
regularizing importance weights. As a byproduct of the calculations, we also
obtain approximate standard errors for estimated predictive errors and for
the comparison of predictive errors between models. We also compute the
widely applicable information criterion (WAIC).

Jonah Gabry

Efficient Leave-One-Out Cross-Validation and WAIC for Bayesian
Models

print.loo function

A list with class <code>'loo'</code> (as returned by <code><a rd-options='' href='loo'>loo</a></code> or
<code><a rd-options='' href='waic'>waic</a></code>).

An integer passed to <code><a rd-options='base' href='round'>round</a></code>.

Logical. If <code>TRUE</code> the estimates of the Pareto shape
parameter $k$ are plotted. Ignored if <code>x</code> was generated by
<code><a rd-options='' href='waic'>waic</a></code>. To just plot $k$ without printing use the
<code><a rd-options='=pareto-k-diagnostic' href='plot method'>plot method</a></code>.

Arguments passed to <code><a rd-options='' href='plot.loo'>plot.loo</a></code> if <code>plot_k</code> is
<code>TRUE</code>.

print.loo: Print method for 'loo' objects

Description

Usage

Arguments

Value

See Also