predict.hglm

Obtains predictions from a fitted holistic generalized linear model object.

Holistic generalized linear models (HGLMs) extend generalized linear models (GLMs) by enabling the possibility to add further constraints to the model. The 'holiglm' package simplifies estimating HGLMs using convex optimization. Additional information about the package can be found in the reference manual, the 'README' and the accompanying paper <doi:10.18637/jss.v108.i07>.

Benjamin Schwendinger

holiglm

Holistic Generalized Linear Models

Florian Schwendinger

Laura Vana

predict.hglm function

<dl><dt>object</dt>
<dd>a fitted object of class inheriting from "hglm".</dd>
<dt>newdata</dt>
<dd>an optional data frame containing new observations for which
predictions are to be made. If ommitted, the fitted linear predictors are
used.</dd>
<dt>type</dt>
<dd>the type of predictions to be made. Possible values are
<code>"link"</code> (default) or <code>"response"</code>. If <code>"link"</code>, the
predictions are in the link scale; if <code>"response"</code>, the predictions
are transformed to the response scale.</dd>
<dt>...</dt>
<dd>optional arguments currently ignored.</dd></dl>

Arguments

Predict Method for HGLM Fits — predict.hglm

<dl>

<dt>object</dt>
<dd>a fitted object of class inheriting from "hglm".</dd>


<dt>newdata</dt>
<dd>an optional data frame containing new observations for which
predictions are to be made. If ommitted, the fitted linear predictors are
used.</dd>


<dt>type</dt>
<dd>the type of predictions to be made. Possible values are
<code>"link"</code> (default) or <code>"response"</code>. If <code>"link"</code>, the
predictions are in the link scale; if <code>"response"</code>, the predictions
are transformed to the response scale.</dd>


<dt>...</dt>
<dd>optional arguments currently ignored.</dd>

</dl>

predict.hglm: Predict Method for HGLM Fits

Description

Usage

Value

Arguments

Examples