predict.gldrm

Obtains predicted probabilities, predicted class, or linear predictors.

Fits a generalized linear density ratio model (GLDRM).
A GLDRM is a semiparametric generalized linear model.
In contrast to a GLM, which assumes a particular exponential family distribution,
the GLDRM uses a semiparametric likelihood to estimate the reference distribution.
The reference distribution may be any discrete, continuous, or mixed exponential
family distribution. The model parameters, which include both the regression
coefficients and the cdf of the unspecified reference distribution, are estimated
by maximizing a semiparametric likelihood. Regression coefficients are estimated
with no loss of efficiency, i.e. the asymptotic variance is the same as if the
true exponential family distribution were known.
Huang (2014) <doi:10.1080/01621459.2013.824892>.
Huang and Rathouz (2012) <doi:10.1093/biomet/asr075>.
Rathouz and Gao (2008) <doi:10.1093/biostatistics/kxn030>.

Michael Wurm

gldrm

Generalized Linear Density Ratio Models

Paul Rathouz

predict.gldrm function

<dl><dt>object</dt>
<dd>S3 object of class "gldrm", returned from the <code>gldrm</code> function.</dd>
<dt>newdata</dt>
<dd>Optional data frame. If NULL, fitted values will be obtained
for the training data.</dd>
<dt>type</dt>
<dd>The type of prediction required. Type "link" returns the linear
predictor. Type "response" returns the fitted mean. Type "terms" returns
a matrix giving the fitted values of each term in the model formula on the
linear predictor scale. Type "fTilt" returns a matrix containing the
fitted nonparametric distribution for each observation. Each row of the matrix
corresponds to an observation in <code>newdata</code>, and each column corresponds
to a unique response value in the training data.</dd>
<dt>se.fit</dt>
<dd>Logical. If TRUE, standard errors are also returned. Does not apply
for <code>type = "fTilt"</code>.</dd>
<dt>offset</dt>
<dd>Optional offset vector. Only used if <code>newdata</code> is not NULL.</dd>
<dt>...</dt>
<dd>Not used. Additional predict arguments.</dd></dl>

Arguments

Predict method for a gldrm object — predict.gldrm

<dl>

<dt>object</dt>
<dd>S3 object of class "gldrm", returned from the <code>gldrm</code> function.</dd>


<dt>newdata</dt>
<dd>Optional data frame. If NULL, fitted values will be obtained
for the training data.</dd>


<dt>type</dt>
<dd>The type of prediction required. Type "link" returns the linear
predictor. Type "response" returns the fitted mean. Type "terms" returns
a matrix giving the fitted values of each term in the model formula on the
linear predictor scale. Type "fTilt" returns a matrix containing the
fitted nonparametric distribution for each observation. Each row of the matrix
corresponds to an observation in <code>newdata</code>, and each column corresponds
to a unique response value in the training data.</dd>


<dt>se.fit</dt>
<dd>Logical. If TRUE, standard errors are also returned. Does not apply
for <code>type = "fTilt"</code>.</dd>


<dt>offset</dt>
<dd>Optional offset vector. Only used if <code>newdata</code> is not NULL.</dd>


<dt>...</dt>
<dd>Not used. Additional predict arguments.</dd>

</dl>

predict.gldrm: Predict method for a gldrm object

Description

Usage

Value

Arguments