qrnn.initialize

covariate matrix with number of rows equal to the number of samples and number of columns equal to the number of variables.

response column matrix with number of rows equal to the number of samples.

number of hidden nodes in the QRNN model.

n.hidden

initial weight range for input-hidden and hidden-output weight matrices.

init.range

Random initialization of the weight vector used during fitting of a QRNN model.

Fit quantile regression neural network models with optional
left censoring, partial monotonicity constraints, generalized additive
model constraints, and the ability to fit multiple non-crossing quantile
functions following Cannon (2011) <doi:10.1016/j.cageo.2010.07.005>
and Cannon (2018) <doi:10.1007/s00477-018-1573-6>.

Alex Cannon

qrnn

Quantile Regression Neural Network

Alex J. Cannon

qrnn.initialize function

<dl> <dt>x</dt>
<dd>covariate matrix with number of rows equal to the number of samples and number of columns equal to the number of variables.</dd> <dt>y</dt>
<dd>response column matrix with number of rows equal to the number of samples.</dd> <dt>n.hidden</dt>
<dd>number of hidden nodes in the QRNN model.</dd> <dt>init.range</dt>
<dd>initial weight range for input-hidden and hidden-output weight matrices.</dd></dl>

Arguments

Initialize a QRNN weight vector — qrnn.initialize

<dl>

 <dt>x</dt>
<dd>covariate matrix with number of rows equal to the number of samples and number of columns equal to the number of variables.</dd>

 <dt>y</dt>
<dd>response column matrix with number of rows equal to the number of samples.</dd>

 <dt>n.hidden</dt>
<dd>number of hidden nodes in the QRNN model.</dd>

 <dt>init.range</dt>
<dd>initial weight range for input-hidden and hidden-output weight matrices.</dd>

</dl>

qrnn.initialize: Initialize a QRNN weight vector

Description

Usage

Arguments