GetPredictorMatrix

model.matrix

Spike and slab regression with a variety of residual error
distributions corresponding to Gaussian, Student T, probit, logit, SVM, and a
few others. Spike and slab regression is Bayesian regression with prior
distributions containing a point mass at zero. The posterior updates the
amount of mass on this point, leading to a posterior distribution that is
actually sparse, in the sense that if you sample from it many coefficients are
actually zeros. Sampling from this posterior distribution is an elegant way
to handle Bayesian variable selection and model averaging. See
<DOI:10.1504/IJMMNO.2014.059942> for an explanation of the Gaussian case.

Steven Scott

BoomSpikeSlab

MCMC for Spike and Slab Regression

model.matrix function

<dl> <dt>object</dt>
<dd>An object of class glm.spike. The object must be a
 list with the following elements<ul>
<li>beta: a matrix of MCMC draws, with rows representing draws,
 and columns representing coefficients.</li>
<li>xlevels: the levels of any contrasts present in the original
 training data.</li>
<li>contrasts: the "contrasts" attribute of the original design
 matrix used to train the model.</li>
<li>terms: the terms of the formula used to fit the original model.</li>
</ul></dd>
 <dt>newdata</dt>
<dd>A data frame, matrix, or vector containing the
 predictors needed to make a prediction. If newdata is a
 matrix it must have the same number of columns as
 length(object$beta), unless it is off by one and the model
 contains an intercept, in which case an intercept term will
 be added. If length(object$beta) == 1 (or 2, with one
 element containing an intercept) then newdata can be a
 numeric vector.</dd>
 <dt>na.action</dt>
<dd>A function specifying what to do with <code>NA</code>'s.</dd>
 <dt>...</dt>
<dd>Extra arguments passed to <code><a href="/link/model.matrix?package=BoomSpikeSlab&version=1.2.6" data-mini-rdoc="BoomSpikeSlab::model.matrix">model.matrix</a></code>, in the event
 that <code>newdata</code> is a data frame.</dd>
</dl>

Arguments

Author

GetPredictorMatrix — model.matrix

<dl>

 <dt>object</dt>
<dd>An object of class glm.spike. The object must be a
 list with the following elements<ul>
<li>beta: a matrix of MCMC draws, with rows representing draws,
 and columns representing coefficients.</li>
<li>xlevels: the levels of any contrasts present in the original
 training data.</li>
<li>contrasts: the "contrasts" attribute of the original design
 matrix used to train the model.</li>
<li>terms: the terms of the formula used to fit the original model.</li>
</ul></dd>


 <dt>newdata</dt>
<dd>A data frame, matrix, or vector containing the
 predictors needed to make a prediction. If newdata is a
 matrix it must have the same number of columns as
 length(object$beta), unless it is off by one and the model
 contains an intercept, in which case an intercept term will
 be added. If length(object$beta) == 1 (or 2, with one
 element containing an intercept) then newdata can be a
 numeric vector.</dd>


 <dt>na.action</dt>
<dd>A function specifying what to do with <code>NA</code>'s.</dd>


 <dt>...</dt>
<dd>Extra arguments passed to <code><a href='https://rdrr.io/r/stats/model.matrix.html'>model.matrix</a></code>, in the event
 that <code>newdata</code> is a data frame.</dd>


</dl>

model.matrix: GetPredictorMatrix

Description

Usage

Value

Arguments

Author

See Also