plot.retlev

<code>plot</code> method for an objects of class <code>c("retlev", "lax")</code>.

Performs adjusted inferences based on model objects fitted, using
maximum likelihood estimation, by the extreme value analysis packages
'eva' <https://cran.r-project.org/package=eva>,
'evd' <https://cran.r-project.org/package=evd>,
'evir' <https://cran.r-project.org/package=evir>,
'extRemes' <https://cran.r-project.org/package=extRemes>,
'fExtremes' <https://cran.r-project.org/package=fExtremes>,
'ismev' <https://cran.r-project.org/package=ismev>,
'mev' <https://cran.r-project.org/package=mev>,
'POT' <https://cran.r-project.org/package=POT> and
'texmex' <https://cran.r-project.org/package=texmex>.
Adjusted standard errors and an adjusted loglikelihood are provided, using
the 'chandwich' package <https://cran.r-project.org/package=chandwich>
and the object-oriented features of the 'sandwich' package
<https://cran.r-project.org/package=sandwich>. The adjustment is based on a
robust sandwich estimator of the parameter covariance matrix, based on the
methodology in Chandler and Bate (2007) <doi:10.1093/biomet/asm015>. This
can be used for cluster correlated data when interest lies in the
parameters of the marginal distributions, or for performing inferences that
are robust to certain types of model misspecification. Univariate extreme
value models, including regression models, are supported.

Paul Northrop

Loglikelihood Adjustment for Extreme Value Models

Camellia Yin

plot.retlev function

<dl><dt>x</dt>
<dd>an object of class <code>c("retlev", "lax")</code>, a result of
a call to <code>return_level</code>, using <code>prof = TRUE</code>.</dd>
<dt>y</dt>
<dd>Not used.</dd>
<dt>level</dt>
<dd>A numeric scalar in (0, 1). The confidence level required for
the confidence interval for the <code>m</code>-year return level.
If <code>level</code> is not supplied then <code>x$level</code> is used.
<code>level</code> must be no larger than <code>x$level</code>.</dd>
<dt>legend</dt>
<dd>A logical scalar. Should we add a legend (in the top right
of the plot) that gives the approximate values of the MLE and
100<code>level</code>% confidence limits?</dd>
<dt>digits</dt>
<dd>An integer. Passed to <code>signif</code> to
round the values in the legend.</dd>
<dt>plot</dt>
<dd>A logical scalar. If <code>TRUE</code> then the plot is produced.
Otherwise, it is not, but the MLE and confidence limits are returned.</dd>
<dt>...</dt>
<dd>Further arguments to be passed to
<code><a href="/link/plot?package=lax&version=1.2.3" data-mini-rdoc="lax::plot">plot</a></code>.</dd></dl>

Arguments

See the examples in <code>return_level</code>.

Examples

Plot diagnostics for a retlev object — plot.retlev

<dl>

<dt>x</dt>
<dd>an object of class <code>c("retlev", "lax")</code>, a result of
a call to <code>return_level</code>, using <code>prof = TRUE</code>.</dd>


<dt>y</dt>
<dd>Not used.</dd>


<dt>level</dt>
<dd>A numeric scalar in (0, 1). The confidence level required for
the confidence interval for the <code>m</code>-year return level.
If <code>level</code> is not supplied then <code>x$level</code> is used.
<code>level</code> must be no larger than <code>x$level</code>.</dd>


<dt>legend</dt>
<dd>A logical scalar. Should we add a legend (in the top right
of the plot) that gives the approximate values of the MLE and
100<code>level</code>% confidence limits?</dd>


<dt>digits</dt>
<dd>An integer. Passed to <code>signif</code> to
round the values in the legend.</dd>


<dt>plot</dt>
<dd>A logical scalar. If <code>TRUE</code> then the plot is produced.
Otherwise, it is not, but the MLE and confidence limits are returned.</dd>


<dt>...</dt>
<dd>Further arguments to be passed to
<code><a href='https://rdrr.io/r/graphics/plot.default.html'>plot</a></code>.</dd>

</dl>

See the examples in <code>return_level</code>.

plot.retlev: Plot diagnostics for a retlev object

Description

Usage

Value

Arguments

Examples

Details

See Also