tDist-class

This class provides objects representing scaled <em>t</em> distributions.

classes

distribution

Methods and classes to build HMMs
that are suitable for the analysis of ChIP-chip data. The
provided parameter estimation methods include the Baum-Welch
algorithm and Viterbi training as well as a combination of
both.

Peter Humburg

tileHMM

Hidden Markov Models for ChIP-on-Chip Analysis

tDist-class function

Objects can be created by calls of the form <code>new("tDist", mean, var, df)</code>.
	<dl>
      <dt><code>mean</code>:</dt><dd>Location parameter.</dd> <dt><code>var</code>:</dt><dd>Scale parameter.</dd> <dt><code>df</code>:</dt><dd>Degrees of freedom.</dd> </dl> The distribution has density
	$$%
		f(x; \texttt{mean}, \texttt{var}, \texttt{df}) = \frac{\Gamma\left(\frac{\small\texttt{df}+1}{2}\right)}{%
		\sqrt{\small\texttt{var}\times\pi\times\small\texttt{df}}\,\Gamma\left(\frac{\small\texttt{df}}{2}\right)} \times %
		\frac{1}{\sqrt{\left(1 + \frac{(x-\small\texttt{mean})^2}{\small\texttt{var}\times\small\texttt{df}}\right)^{\small\texttt{df}+1}}}$$

Objects from the Class

<dl>
    <dt><code>components</code>:</dt><dd>Object of class <code>"matrix"</code> with columns <code>weight</code>, <code>mean</code>, 
    <code>variance</code>, and <code>df</code>.  For objects of class <code>"tDist"</code> this matrix has only one row 
    and <code>weight</code> is always 1.</dd> </dl> 

Slots

Class <code>"contDist"</code>, directly.
Class <code>"dist"</code>, by class "contDist", distance 2.

Extends

<dl>
    <dt>sampleObs</dt><dd><code>signature(dist = "tDist", size = "numeric")</code>: Sample <code>size</code> observations from <code>dist</code>.</dd> </dl> 

tDist-class: Class "tDist"

Description

Arguments

Objects from the Class

Slots

Extends

Methods

See Also

Examples