vcov.brnb

an object of class "brnb", usually, a result of a call to <code><a rd-options="" href="/link/brnb?package=brglm2&version=0.8.2" data-mini-rdoc="brglm2::brnb">brnb</a></code>.

object

character specifying for which component of the model variance-covariance matrix should be extracted.

model

for the <code>aov</code>, <code>lm</code>, <code>glm</code>, <code>mlm</code>, and where
 applicable <code>summary.lm</code> etc methods: logical indicating if the
 full variance-covariance matrix should be returned also in case of
 an over-determined system where some coefficients are undefined and
 <code><a rd-options="stats" href="/link/coef?package=brglm2&version=0.8.2&to=stats" data-mini-rdoc="stats::coef">coef</a>(.)</code> contains <code>NA</code>s correspondingly. When
 <code>complete = TRUE</code>, <code>vcov()</code> is compatible with
 <code>coef()</code> also in this singular case.

complete

additional arguments for method functions. For the
 <code><a rd-options="stats" href="/link/glm?package=brglm2&version=0.8.2&to=stats" data-mini-rdoc="stats::glm">glm</a></code> method this can be used to pass a
 <code>dispersion</code> parameter.

Extract model variance-covariance matrix from <code>brnb</code> objects

Estimation and inference from generalized linear models based on various methods for bias reduction and maximum penalized likelihood with powers of the Jeffreys prior as penalty. The 'brglmFit' fitting method can achieve reduction of estimation bias by solving either the mean bias-reducing adjusted score equations in Firth (1993) <doi:10.1093/biomet/80.1.27> and Kosmidis and Firth (2009) <doi:10.1093/biomet/asp055>, or the median bias-reduction adjusted score equations in Kenne et al. (2017) <doi:10.1093/biomet/asx046>, or through the direct subtraction of an estimate of the bias of the maximum likelihood estimator from the maximum likelihood estimates as in Cordeiro and McCullagh (1991) <https://www.jstor.org/stable/2345592>. See Kosmidis et al (2020) <doi:10.1007/s11222-019-09860-6> for more details. Estimation in all cases takes place via a quasi Fisher scoring algorithm, and S3 methods for the construction of of confidence intervals for the reduced-bias estimates are provided. In the special case of generalized linear models for binomial and multinomial responses (both ordinal and nominal), the adjusted score approaches to mean and media bias reduction have been found to return estimates with improved frequentist properties, that are also always finite, even in cases where the maximum likelihood estimates are infinite (e.g. complete and quasi-complete separation; see Kosmidis and Firth, 2020 <doi:10.1093/biomet/asaa052>, for a proof for mean bias reduction in logistic regression).

Ioannis Kosmidis

brglm2

Bias Reduction in Generalized Linear Models

Kjell Konis

Nicola Sartori

vcov.brnb function

<dl><dt>object</dt>
<dd>an object of class "brnb", usually, a result of a call to <code>brnb</code>.</dd>
<dt>model</dt>
<dd>character specifying for which component of the model variance-covariance matrix should be extracted.</dd>
<dt>complete</dt>
<dd>for the <code>aov</code>, <code>lm</code>, <code>glm</code>, <code>mlm</code>, and where
 applicable <code>summary.lm</code> etc methods: logical indicating if the
 full variance-covariance matrix should be returned also in case of
 an over-determined system where some coefficients are undefined and
 <code><a href="/link/coef?package=brglm2&version=0.8.2" data-mini-rdoc="brglm2::coef">coef</a>(.)</code> contains <code>NA</code>s correspondingly. When
 <code>complete = TRUE</code>, <code><a href="/link/vcov()?package=brglm2&version=0.8.2" data-mini-rdoc="brglm2::vcov()">vcov()</a></code> is compatible with
 <code><a href="/link/coef()?package=brglm2&version=0.8.2" data-mini-rdoc="brglm2::coef()">coef()</a></code> also in this singular case.</dd>
<dt>...</dt>
<dd>additional arguments for method functions. For the
 <code><a href="/link/glm?package=brglm2&version=0.8.2" data-mini-rdoc="brglm2::glm">glm</a></code> method this can be used to pass a
 <code>dispersion</code> parameter.</dd></dl>

Arguments

Extract model variance-covariance matrix from brnb objects — vcov.brnb

<dl>

<dt>object</dt>
<dd>an object of class "brnb", usually, a result of a call to <code>brnb</code>.</dd>


<dt>model</dt>
<dd>character specifying for which component of the model variance-covariance matrix should be extracted.</dd>


<dt>complete</dt>
<dd>for the <code>aov</code>, <code>lm</code>, <code>glm</code>, <code>mlm</code>, and where
 applicable <code>summary.lm</code> etc methods: logical indicating if the
 full variance-covariance matrix should be returned also in case of
 an over-determined system where some coefficients are undefined and
 <code><a href='https://rdrr.io/r/stats/coef.html'>coef</a>(.)</code> contains <code>NA</code>s correspondingly. When
 <code>complete = TRUE</code>, <code><a href='https://rdrr.io/r/stats/vcov.html'>vcov()</a></code> is compatible with
 <code><a href='https://rdrr.io/r/stats/coef.html'>coef()</a></code> also in this singular case.</dd>


<dt>...</dt>
<dd>additional arguments for method functions. For the
 <code><a href='https://rdrr.io/r/stats/glm.html'>glm</a></code> method this can be used to pass a
 <code>dispersion</code> parameter.</dd>

</dl>

vcov.brnb: Extract model variance-covariance matrix from `brnb` objects

Description

Usage

Arguments

Details

See Also