161 lines
18 KiB
HTML
161 lines
18 KiB
HTML
<html>
|
||
<head>
|
||
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
|
||
<title>Bivariate Statistics</title>
|
||
<link rel="stylesheet" href="../math.css" type="text/css">
|
||
<meta name="generator" content="DocBook XSL Stylesheets V1.79.1">
|
||
<link rel="home" href="../index.html" title="Math Toolkit 3.0.0">
|
||
<link rel="up" href="../statistics.html" title="Chapter 6. Statistics">
|
||
<link rel="prev" href="univariate_statistics.html" title="Univariate Statistics">
|
||
<link rel="next" href="signal_statistics.html" title="Signal Statistics">
|
||
</head>
|
||
<body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
|
||
<table cellpadding="2" width="100%"><tr>
|
||
<td valign="top"><img alt="Boost C++ Libraries" width="277" height="86" src="../../../../../boost.png"></td>
|
||
<td align="center"><a href="../../../../../index.html">Home</a></td>
|
||
<td align="center"><a href="../../../../../libs/libraries.htm">Libraries</a></td>
|
||
<td align="center"><a href="http://www.boost.org/users/people.html">People</a></td>
|
||
<td align="center"><a href="http://www.boost.org/users/faq.html">FAQ</a></td>
|
||
<td align="center"><a href="../../../../../more/index.htm">More</a></td>
|
||
</tr></table>
|
||
<hr>
|
||
<div class="spirit-nav">
|
||
<a accesskey="p" href="univariate_statistics.html"><img src="../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../statistics.html"><img src="../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../index.html"><img src="../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="signal_statistics.html"><img src="../../../../../doc/src/images/next.png" alt="Next"></a>
|
||
</div>
|
||
<div class="section">
|
||
<div class="titlepage"><div><div><h2 class="title" style="clear: both">
|
||
<a name="math_toolkit.bivariate_statistics"></a><a class="link" href="bivariate_statistics.html" title="Bivariate Statistics">Bivariate Statistics</a>
|
||
</h2></div></div></div>
|
||
<h4>
|
||
<a name="math_toolkit.bivariate_statistics.h0"></a>
|
||
<span class="phrase"><a name="math_toolkit.bivariate_statistics.synopsis"></a></span><a class="link" href="bivariate_statistics.html#math_toolkit.bivariate_statistics.synopsis">Synopsis</a>
|
||
</h4>
|
||
<pre class="programlisting"><span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">math</span><span class="special">/</span><span class="identifier">statistics</span><span class="special">/</span><span class="identifier">bivariate_statistics</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">></span>
|
||
|
||
<span class="keyword">namespace</span> <span class="identifier">boost</span><span class="special">{</span> <span class="keyword">namespace</span> <span class="identifier">math</span><span class="special">{</span> <span class="keyword">namespace</span> <span class="identifier">statistics</span> <span class="special">{</span>
|
||
|
||
<span class="keyword">template</span><span class="special"><</span><span class="keyword">typename</span> <span class="identifier">ExecutionPolicy</span><span class="special">,</span> <span class="keyword">typename</span> <span class="identifier">Container</span><span class="special">></span>
|
||
<span class="keyword">auto</span> <span class="identifier">covariance</span><span class="special">(</span><span class="identifier">ExecutionPolicy</span><span class="special">&&</span> <span class="identifier">exec</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">u</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">v</span><span class="special">);</span>
|
||
|
||
<span class="keyword">template</span><span class="special"><</span><span class="keyword">typename</span> <span class="identifier">Container</span><span class="special">></span>
|
||
<span class="keyword">auto</span> <span class="identifier">covariance</span><span class="special">(</span><span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">u</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">v</span><span class="special">);</span>
|
||
|
||
<span class="keyword">template</span><span class="special"><</span><span class="keyword">typename</span> <span class="identifier">ExecutionPolicy</span><span class="special">,</span> <span class="keyword">typename</span> <span class="identifier">Container</span><span class="special">></span>
|
||
<span class="keyword">auto</span> <span class="identifier">means_and_covariance</span><span class="special">(</span><span class="identifier">ExecutionPolicy</span><span class="special">&&</span> <span class="identifier">exec</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">u</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">v</span><span class="special">);</span>
|
||
|
||
<span class="keyword">template</span><span class="special"><</span><span class="keyword">typename</span> <span class="identifier">Container</span><span class="special">></span>
|
||
<span class="keyword">auto</span> <span class="identifier">means_and_covariance</span><span class="special">(</span><span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">u</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">v</span><span class="special">);</span>
|
||
|
||
<span class="keyword">template</span><span class="special"><</span><span class="keyword">typename</span> <span class="identifier">ExecutionPolicy</span><span class="special">,</span> <span class="keyword">typename</span> <span class="identifier">Container</span><span class="special">></span>
|
||
<span class="keyword">auto</span> <span class="identifier">correlation_coefficient</span><span class="special">(</span><span class="identifier">ExecutionPolicy</span><span class="special">&&</span> <span class="identifier">exec</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">u</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">v</span><span class="special">);</span>
|
||
|
||
<span class="keyword">template</span><span class="special"><</span><span class="keyword">typename</span> <span class="identifier">Container</span><span class="special">></span>
|
||
<span class="keyword">auto</span> <span class="identifier">correlation_coefficient</span><span class="special">(</span><span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">u</span><span class="special">,</span> <span class="identifier">Container</span> <span class="keyword">const</span> <span class="special">&</span> <span class="identifier">v</span><span class="special">);</span>
|
||
|
||
<span class="special">}}}</span>
|
||
</pre>
|
||
<h4>
|
||
<a name="math_toolkit.bivariate_statistics.h1"></a>
|
||
<span class="phrase"><a name="math_toolkit.bivariate_statistics.description"></a></span><a class="link" href="bivariate_statistics.html#math_toolkit.bivariate_statistics.description">Description</a>
|
||
</h4>
|
||
<p>
|
||
This file provides functions for computing bivariate statistics. The functions
|
||
are C++11 compatible, but require C++17 to use execution policies. If an execution
|
||
policy is not passed to the function the default is std::execution::seq.
|
||
</p>
|
||
<h4>
|
||
<a name="math_toolkit.bivariate_statistics.h2"></a>
|
||
<span class="phrase"><a name="math_toolkit.bivariate_statistics.covariance"></a></span><a class="link" href="bivariate_statistics.html#math_toolkit.bivariate_statistics.covariance">Covariance</a>
|
||
</h4>
|
||
<p>
|
||
Computes the population covariance of two datasets:
|
||
</p>
|
||
<pre class="programlisting"><span class="identifier">std</span><span class="special">::</span><span class="identifier">vector</span><span class="special"><</span><span class="keyword">double</span><span class="special">></span> <span class="identifier">u</span><span class="special">{</span><span class="number">1</span><span class="special">,</span><span class="number">2</span><span class="special">,</span><span class="number">3</span><span class="special">,</span><span class="number">4</span><span class="special">,</span><span class="number">5</span><span class="special">};</span>
|
||
<span class="identifier">std</span><span class="special">::</span><span class="identifier">vector</span><span class="special"><</span><span class="keyword">double</span><span class="special">></span> <span class="identifier">v</span><span class="special">{</span><span class="number">1</span><span class="special">,</span><span class="number">2</span><span class="special">,</span><span class="number">3</span><span class="special">,</span><span class="number">4</span><span class="special">,</span><span class="number">5</span><span class="special">};</span>
|
||
<span class="keyword">double</span> <span class="identifier">cov_uv</span> <span class="special">=</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">statistics</span><span class="special">::</span><span class="identifier">covariance</span><span class="special">(</span><span class="identifier">u</span><span class="special">,</span> <span class="identifier">v</span><span class="special">);</span>
|
||
</pre>
|
||
<p>
|
||
The implementation follows <a href="https://doi.org/10.1109/CLUSTR.2009.5289161" target="_top">Bennet
|
||
et al</a>. The parallel implementation follows <a href="https://dl.acm.org/doi/10.1145/3221269.3223036" target="_top">Schubert
|
||
et al</a>. The data is not modified. Works with real-valued inputs and
|
||
does not work with complex-valued inputs.
|
||
</p>
|
||
<p>
|
||
<span class="emphasis"><em>Nota bene:</em></span> If the input is an integer type the output
|
||
will be a double precision type.
|
||
</p>
|
||
<p>
|
||
The algorithm used herein simultaneously generates the mean values of the input
|
||
data <span class="emphasis"><em>u</em></span> and <span class="emphasis"><em>v</em></span>. For certain applications,
|
||
it might be useful to get them in a single pass through the data. As such,
|
||
we provide <code class="computeroutput"><span class="identifier">means_and_covariance</span></code>:
|
||
</p>
|
||
<pre class="programlisting"><span class="identifier">std</span><span class="special">::</span><span class="identifier">vector</span><span class="special"><</span><span class="keyword">double</span><span class="special">></span> <span class="identifier">u</span><span class="special">{</span><span class="number">1</span><span class="special">,</span><span class="number">2</span><span class="special">,</span><span class="number">3</span><span class="special">,</span><span class="number">4</span><span class="special">,</span><span class="number">5</span><span class="special">};</span>
|
||
<span class="identifier">std</span><span class="special">::</span><span class="identifier">vector</span><span class="special"><</span><span class="keyword">double</span><span class="special">></span> <span class="identifier">v</span><span class="special">{</span><span class="number">1</span><span class="special">,</span><span class="number">2</span><span class="special">,</span><span class="number">3</span><span class="special">,</span><span class="number">4</span><span class="special">,</span><span class="number">5</span><span class="special">};</span>
|
||
<span class="keyword">auto</span> <span class="special">[</span><span class="identifier">mu_u</span><span class="special">,</span> <span class="identifier">mu_v</span><span class="special">,</span> <span class="identifier">cov_uv</span><span class="special">]</span> <span class="special">=</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">statistics</span><span class="special">::</span><span class="identifier">means_and_covariance</span><span class="special">(</span><span class="identifier">u</span><span class="special">,</span> <span class="identifier">v</span><span class="special">);</span>
|
||
</pre>
|
||
<h4>
|
||
<a name="math_toolkit.bivariate_statistics.h3"></a>
|
||
<span class="phrase"><a name="math_toolkit.bivariate_statistics.correlation_coefficient"></a></span><a class="link" href="bivariate_statistics.html#math_toolkit.bivariate_statistics.correlation_coefficient">Correlation
|
||
Coefficient</a>
|
||
</h4>
|
||
<p>
|
||
Computes the <a href="https://en.wikipedia.org/wiki/Pearson_correlation_coefficient" target="_top">Pearson
|
||
correlation coefficient</a> of two datasets <span class="emphasis"><em>u</em></span> and
|
||
<span class="emphasis"><em>v</em></span>:
|
||
</p>
|
||
<pre class="programlisting"><span class="identifier">std</span><span class="special">::</span><span class="identifier">vector</span><span class="special"><</span><span class="keyword">double</span><span class="special">></span> <span class="identifier">u</span><span class="special">{</span><span class="number">1</span><span class="special">,</span><span class="number">2</span><span class="special">,</span><span class="number">3</span><span class="special">,</span><span class="number">4</span><span class="special">,</span><span class="number">5</span><span class="special">};</span>
|
||
<span class="identifier">std</span><span class="special">::</span><span class="identifier">vector</span><span class="special"><</span><span class="keyword">double</span><span class="special">></span> <span class="identifier">v</span><span class="special">{</span><span class="number">1</span><span class="special">,</span><span class="number">2</span><span class="special">,</span><span class="number">3</span><span class="special">,</span><span class="number">4</span><span class="special">,</span><span class="number">5</span><span class="special">};</span>
|
||
<span class="keyword">double</span> <span class="identifier">rho_uv</span> <span class="special">=</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">statistics</span><span class="special">::</span><span class="identifier">correlation_coefficient</span><span class="special">(</span><span class="identifier">u</span><span class="special">,</span> <span class="identifier">v</span><span class="special">);</span>
|
||
<span class="comment">// rho_uv = 1.</span>
|
||
</pre>
|
||
<p>
|
||
Works with real-valued inputs and does not work with complex-valued inputs.
|
||
</p>
|
||
<p>
|
||
<span class="emphasis"><em>Nota bene:</em></span> If the input is an integer type the output
|
||
will be a double precision type.
|
||
</p>
|
||
<p>
|
||
If one or both of the datasets is constant, the correlation coefficient is
|
||
an indeterminant form (0/0) and definitions must be introduced to assign it
|
||
a value. We use the following: If both datasets are constant, then the correlation
|
||
coefficient is 1. If one dataset is constant, and the other is not, then the
|
||
correlation coefficient is zero.
|
||
</p>
|
||
<h4>
|
||
<a name="math_toolkit.bivariate_statistics.h4"></a>
|
||
<span class="phrase"><a name="math_toolkit.bivariate_statistics.references"></a></span><a class="link" href="bivariate_statistics.html#math_toolkit.bivariate_statistics.references">References</a>
|
||
</h4>
|
||
<div class="itemizedlist"><ul class="itemizedlist" style="list-style-type: disc; ">
|
||
<li class="listitem">
|
||
Bennett, Janine, et al. <span class="emphasis"><em>Numerically stable, single-pass, parallel
|
||
statistics algorithms.</em></span> Cluster Computing and Workshops, 2009.
|
||
CLUSTER'09. IEEE International Conference on. IEEE, 2009.
|
||
</li>
|
||
<li class="listitem">
|
||
Schubert, Erich; Gertz, Michael <span class="emphasis"><em>Numerically stable parallel computation
|
||
of (co-)variance'</em></span> Proceedings of the 30th International Conference
|
||
on Scientific and Statistical Database Management, 2018.
|
||
</li>
|
||
</ul></div>
|
||
</div>
|
||
<table xmlns:rev="http://www.cs.rpi.edu/~gregod/boost/tools/doc/revision" width="100%"><tr>
|
||
<td align="left"></td>
|
||
<td align="right"><div class="copyright-footer">Copyright © 2006-2021 Nikhar Agrawal, Anton Bikineev, Matthew Borland,
|
||
Paul A. Bristow, Marco Guazzone, Christopher Kormanyos, Hubert Holin, Bruno
|
||
Lalande, John Maddock, Evan Miller, Jeremy Murphy, Matthew Pulver, Johan Råde,
|
||
Gautam Sewani, Benjamin Sobotta, Nicholas Thompson, Thijs van den Berg, Daryle
|
||
Walker and Xiaogang Zhang<p>
|
||
Distributed under the Boost Software License, Version 1.0. (See accompanying
|
||
file LICENSE_1_0.txt or copy at <a href="http://www.boost.org/LICENSE_1_0.txt" target="_top">http://www.boost.org/LICENSE_1_0.txt</a>)
|
||
</p>
|
||
</div></td>
|
||
</tr></table>
|
||
<hr>
|
||
<div class="spirit-nav">
|
||
<a accesskey="p" href="univariate_statistics.html"><img src="../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../statistics.html"><img src="../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../index.html"><img src="../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="signal_statistics.html"><img src="../../../../../doc/src/images/next.png" alt="Next"></a>
|
||
</div>
|
||
</body>
|
||
</html>
|