predict.ebnm

The <code><a href="/link/predict?package=ebnm&version=1.1-2" data-mini-rdoc="ebnm::predict">predict</a></code> method for class <code>ebnm</code>.

Provides simple, fast, and stable functions to fit the normal
means model using empirical Bayes. For available models and details, see
function ebnm(). A detailed introduction to the package is provided
by Willwerscheid and Stephens (2021) <arXiv:2110.00152>.

Peter Carbonetto

ebnm

Solve the Empirical Bayes Normal Means Problem

Jason Willwerscheid

Matthew Stephens

Andrew Goldstein

Yusha Liu

predict.ebnm function

<dl><dt>object</dt>
<dd>The fitted <code>ebnm</code> object.</dd>
<dt>newdata</dt>
<dd>A vector of new observations. Missing observations
(<code>NA</code>s) are not allowed.</dd>
<dt>s</dt>
<dd>A vector of standard errors (or a scalar if all are equal).
Standard errors may not be exactly zero, and
missing standard errors are not allowed. Two prior families have
additional restrictions: when horseshoe priors are used, errors
must be homoskedastic; and since function
<code>deconv</code> in package <code>deconvolveR</code> takes
\(z\)-scores, the "deconvolver" family requires that all standard errors
be equal to 1.</dd>
<dt>...</dt>
<dd>Not used. Included for consistency as an S3 method.</dd></dl>

Arguments

The <code><a href='https://rdrr.io/r/stats/predict.html'>predict</a></code> method for class <code>ebnm</code>.

Use the estimated prior from a fitted EBNM model to solve the EBNM problem for
  new data — predict.ebnm

<dl>

<dt>object</dt>
<dd>The fitted <code>ebnm</code> object.</dd>


<dt>newdata</dt>
<dd>A vector of new observations. Missing observations
(<code>NA</code>s) are not allowed.</dd>


<dt>s</dt>
<dd>A vector of standard errors (or a scalar if all are equal).
Standard errors may not be exactly zero, and
missing standard errors are not allowed. Two prior families have
additional restrictions: when horseshoe priors are used, errors
must be homoskedastic; and since function
<code>deconv</code> in package <code>deconvolveR</code> takes
\(z\)-scores, the "deconvolver" family requires that all standard errors
be equal to 1.</dd>


<dt>...</dt>
<dd>Not used. Included for consistency as an S3 method.</dd>

</dl>

predict.ebnm: Use the estimated prior from a fitted EBNM model to solve the EBNM problem for new data

Description

Usage

Value

Arguments