htlr_predict

This function uses MCMC samples from fitted <code>htlrfit</code> object OR user supplied 
regression coefficient to predict the class labels of test cases.

internal

Efficient Bayesian multinomial logistic regression based on heavy-tailed
(hyper-LASSO, non-convex) priors. The posterior of coefficients and hyper-parameters
is sampled with restricted Gibbs sampling for leveraging the high-dimensionality and
Hamiltonian Monte Carlo for handling the high-correlation among coefficients. A detailed
description of the method: Li and Yao (2018),
Journal of Statistical Computation and Simulation, 88:14, 2827-2851, <arXiv:1405.3319>.

Longhai Li

HTLR

Bayesian Logistic Regression with Heavy-Tailed Priors

Steven Liu

htlr_predict function

<dl><dt>X_ts</dt>
<dd>Matrix of values at which predictions are to be made.</dd>
<dt>fithtlr</dt>
<dd>Fitted HTLR model object.</dd>
<dt>deltas</dt>
<dd>The values of deltas (for example true deltas) used to make prediction; 
will override <code>fithtlr</code> if provided.</dd>
<dt>burn, thin</dt>
<dd><code>burn</code> of Markov chain (super)iterations will be discarded for prediction,
and only every <code>thin</code> are used.</dd>
<dt>usedmc</dt>
<dd>Indices of Markov chain iterations used for inference. 
If supplied, <code>burn</code> and <code>thin</code> will be ignored.</dd>
<dt>rep.legacy</dt>
<dd>To reproduce (actually incorrect) results in legacy version.
See <a href="https://github.com/longhaiSK/HTLR/issues/7">https://github.com/longhaiSK/HTLR/issues/7</a>.</dd></dl>

Arguments

Make Prediction on New Data (Advanced) — htlr_predict

<dl>

<dt>X_ts</dt>
<dd>Matrix of values at which predictions are to be made.</dd>


<dt>fithtlr</dt>
<dd>Fitted HTLR model object.</dd>


<dt>deltas</dt>
<dd>The values of deltas (for example true deltas) used to make prediction; 
will override <code>fithtlr</code> if provided.</dd>


<dt>burn, thin</dt>
<dd><code>burn</code> of Markov chain (super)iterations will be discarded for prediction,
and only every <code>thin</code> are used.</dd>


<dt>usedmc</dt>
<dd>Indices of Markov chain iterations used for inference. 
If supplied, <code>burn</code> and <code>thin</code> will be ignored.</dd>


<dt>rep.legacy</dt>
<dd>To reproduce (actually incorrect) results in legacy version.
See <a href='https://github.com/longhaiSK/HTLR/issues/7'>https://github.com/longhaiSK/HTLR/issues/7</a>.</dd>

</dl>

htlr_predict: Make Prediction on New Data (Advanced)

Description

Usage

Value

Arguments