Google Git
Sign in
nest-open-source / nest-learning-thermostat / 5.0 / boost / 317601cb979f96545d0e892ce7cfdf59f676ee0a / . / boost_1_45_0 / libs / math / doc / sf_and_dist / html / math_toolkit / dist / stat_tut / weg / find_eg / find_mean_and_sd_eg.html
blob: 66de6abab323e06607971f4576dfd74e3e6dcb0a [file] [log] [blame]
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=US-ASCII">
<title>Find mean and standard deviation example</title>
<link rel="stylesheet" href="../../../../../../../../../../doc/src/boostbook.css" type="text/css">
<meta name="generator" content="DocBook XSL Stylesheets V1.74.0">
<link rel="home" href="../../../../../index.html" title="Math Toolkit">
<link rel="up" href="../find_eg.html" title="Find Location and Scale Examples">
<link rel="prev" href="find_scale_eg.html" title="Find Scale (Standard Deviation) Example">
<link rel="next" href="../nag_library.html" title="Comparison with C, R, FORTRAN-style Free Functions">
</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="find_scale_eg.html"><img src="../../../../../../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../find_eg.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="../nag_library.html"><img src="../../../../../../../../../../doc/src/images/next.png" alt="Next"></a>
</div>
<div class="section" lang="en">
<div class="titlepage"><div><div><h6 class="title">
<a name="math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg"></a><a class="link" href="find_mean_and_sd_eg.html" title="Find mean and standard deviation example">
Find mean and standard deviation example</a>
</h6></div></div></div>
<p>
</p>
<p>
First we need some includes to access the normal distribution, the
algorithms to find location and scale (and some std output of course).
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">math</span><span class="special">/</span><span class="identifier">distributions</span><span class="special">/</span><span class="identifier">normal</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span> <span class="comment">// for normal_distribution
</span> <span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">normal</span><span class="special">;</span> <span class="comment">// typedef provides default type is double.
</span><span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">math</span><span class="special">/</span><span class="identifier">distributions</span><span class="special">/</span><span class="identifier">cauchy</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span> <span class="comment">// for cauchy_distribution
</span> <span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">cauchy</span><span class="special">;</span> <span class="comment">// typedef provides default type is double.
</span><span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">math</span><span class="special">/</span><span class="identifier">distributions</span><span class="special">/</span><span class="identifier">find_location</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">find_location</span><span class="special">;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">math</span><span class="special">/</span><span class="identifier">distributions</span><span class="special">/</span><span class="identifier">find_scale</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">find_scale</span><span class="special">;</span>
<span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">complement</span><span class="special">;</span>
<span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">policies</span><span class="special">::</span><span class="identifier">policy</span><span class="special">;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">iostream</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">cout</span><span class="special">;</span> <span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">endl</span><span class="special">;</span> <span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">left</span><span class="special">;</span> <span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">showpoint</span><span class="special">;</span> <span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">noshowpoint</span><span class="special">;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">iomanip</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">setw</span><span class="special">;</span> <span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">setprecision</span><span class="special">;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">limits</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">numeric_limits</span><span class="special">;</span>
<span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">stdexcept</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">exception</span><span class="special">;</span>
</pre>
<p>
</p>
<p>
<a name="math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg.using_find_location_and_find_scale_to_meet_dispensing_and_measurement_specifications"></a>
</p>
<h5>
<a name="id993230"></a>
<a class="link" href="find_mean_and_sd_eg.html#math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg.using_find_location_and_find_scale_to_meet_dispensing_and_measurement_specifications">Using
find_location and find_scale to meet dispensing and measurement specifications</a>
</h5>
<p>
</p>
<p>
Consider an example from K Krishnamoorthy, Handbook of Statistical
Distributions with Applications, ISBN 1-58488-635-8, (2006) p 126,
example 10.3.7.
</p>
<p>
</p>
<p>
"A machine is set to pack 3 kg of ground beef per pack. Over
a long period of time it is found that the average packed was 3 kg
with a standard deviation of 0.1 kg. Assume the packing is normally
distributed."
</p>
<p>
</p>
<p>
We start by constructing a normal distribution with the given parameters:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">mean</span> <span class="special">=</span> <span class="number">3.</span><span class="special">;</span> <span class="comment">// kg
</span><span class="keyword">double</span> <span class="identifier">standard_deviation</span> <span class="special">=</span> <span class="number">0.1</span><span class="special">;</span> <span class="comment">// kg
</span><span class="identifier">normal</span> <span class="identifier">packs</span><span class="special">(</span><span class="identifier">mean</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span></pre>
<p>
</p>
<p>
</p>
<p>
We can then find the fraction (or %) of packages that weigh more
than 3.1 kg.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">max_weight</span> <span class="special">=</span> <span class="number">3.1</span><span class="special">;</span> <span class="comment">// kg
</span><span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Percentage of packs &gt; "</span> <span class="special">&lt;&lt;</span> <span class="identifier">max_weight</span> <span class="special">&lt;&lt;</span> <span class="string">" is "</span>
<span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">packs</span><span class="special">,</span> <span class="identifier">max_weight</span><span class="special">))</span> <span class="special">*</span> <span class="number">100.</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span> <span class="comment">// P(X &gt; 3.1)</span></pre>
<p>
</p>
<p>
</p>
<p>
We might want to ensure that 95% of packs are over a minimum weight
specification, then we want the value of the mean such that P(X &lt;
2.9) = 0.05.
</p>
<p>
</p>
<p>
Using the mean of 3 kg, we can estimate the fraction of packs that
fail to meet the specification of 2.9 kg.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">minimum_weight</span> <span class="special">=</span> <span class="number">2.9</span><span class="special">;</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span><span class="string">"Fraction of packs &lt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span> <span class="special">&lt;&lt;</span> <span class="string">" with a mean of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">mean</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">packs</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// fraction of packs &lt;= 2.9 with a mean of 3 is 0.841345</span></pre>
<p>
</p>
<p>
</p>
<p>
This is 0.84 - more than the target fraction of 0.95. If we want
95% to be over the minimum weight, what should we set the mean weight
to be?
</p>
<p>
</p>
<p>
Using the KK StatCalc program supplied with the book and the method
given on page 126 gives 3.06449.
</p>
<p>
</p>
<p>
We can confirm this by constructing a new distribution which we call
'xpacks' with a safety margin mean of 3.06449 thus:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">over_mean</span> <span class="special">=</span> <span class="number">3.06449</span><span class="special">;</span>
<span class="identifier">normal</span> <span class="identifier">xpacks</span><span class="special">(</span><span class="identifier">over_mean</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span>
<span class="special">&lt;&lt;</span> <span class="string">" with a mean of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">xpacks</span><span class="special">.</span><span class="identifier">mean</span><span class="special">()</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">xpacks</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// fraction of packs &gt;= 2.9 with a mean of 3.06449 is 0.950005</span></pre>
<p>
</p>
<p>
</p>
<p>
Using this Math Toolkit, we can calculate the required mean directly
thus:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">under_fraction</span> <span class="special">=</span> <span class="number">0.05</span><span class="special">;</span> <span class="comment">// so 95% are above the minimum weight mean - sd = 2.9
</span><span class="keyword">double</span> <span class="identifier">low_limit</span> <span class="special">=</span> <span class="identifier">standard_deviation</span><span class="special">;</span>
<span class="keyword">double</span> <span class="identifier">offset</span> <span class="special">=</span> <span class="identifier">mean</span> <span class="special">-</span> <span class="identifier">low_limit</span> <span class="special">-</span> <span class="identifier">quantile</span><span class="special">(</span><span class="identifier">packs</span><span class="special">,</span> <span class="identifier">under_fraction</span><span class="special">);</span>
<span class="keyword">double</span> <span class="identifier">nominal_mean</span> <span class="special">=</span> <span class="identifier">mean</span> <span class="special">+</span> <span class="identifier">offset</span><span class="special">;</span>
<span class="comment">// mean + (mean - low_limit - quantile(packs, under_fraction));
</span>
<span class="identifier">normal</span> <span class="identifier">nominal_packs</span><span class="special">(</span><span class="identifier">nominal_mean</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Setting the packer to "</span> <span class="special">&lt;&lt;</span> <span class="identifier">nominal_mean</span> <span class="special">&lt;&lt;</span> <span class="string">" will mean that "</span>
<span class="special">&lt;&lt;</span> <span class="string">"fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">nominal_packs</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Setting the packer to 3.06449 will mean that fraction of packs &gt;= 2.9 is 0.95</span></pre>
<p>
</p>
<p>
</p>
<p>
This calculation is generalized as the free function called <a class="link" href="../../../dist_ref/dist_algorithms.html" title="Distribution Algorithms">find_location</a>.
</p>
<p>
</p>
<p>
To use this we will need to
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="preprocessor">#include</span> <span class="special">&lt;</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">math</span><span class="special">/</span><span class="identifier">distributions</span><span class="special">/</span><span class="identifier">find_location</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">&gt;</span>
<span class="keyword">using</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">math</span><span class="special">::</span><span class="identifier">find_location</span><span class="special">;</span></pre>
<p>
</p>
<p>
</p>
<p>
and then use find_location function to find safe_mean, &amp; construct
a new normal distribution called 'goodpacks'.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">safe_mean</span> <span class="special">=</span> <span class="identifier">find_location</span><span class="special">&lt;</span><span class="identifier">normal</span><span class="special">&gt;(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="identifier">under_fraction</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span>
<span class="identifier">normal</span> <span class="identifier">good_packs</span><span class="special">(</span><span class="identifier">safe_mean</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span></pre>
<p>
</p>
<p>
</p>
<p>
with the same confirmation as before:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Setting the packer to "</span> <span class="special">&lt;&lt;</span> <span class="identifier">nominal_mean</span> <span class="special">&lt;&lt;</span> <span class="string">" will mean that "</span>
<span class="special">&lt;&lt;</span> <span class="string">"fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">good_packs</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Setting the packer to 3.06449 will mean that fraction of packs &gt;= 2.9 is 0.95</span></pre>
<p>
</p>
<p>
<a name="math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg.using_cauchy_lorentz_instead_of_normal_distribution"></a>
</p>
<h5>
<a name="id994412"></a>
<a class="link" href="find_mean_and_sd_eg.html#math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg.using_cauchy_lorentz_instead_of_normal_distribution">Using
Cauchy-Lorentz instead of normal distribution</a>
</h5>
<p>
</p>
<p>
After examining the weight distribution of a large number of packs,
we might decide that, after all, the assumption of a normal distribution
is not really justified. We might find that the fit is better to
a <a class="link" href="../../../dist_ref/dists/cauchy_dist.html" title="Cauchy-Lorentz Distribution">Cauchy
Distribution</a>. This distribution has wider 'wings', so that
whereas most of the values are closer to the mean than the normal,
there are also more values than 'normal' that lie further from the
mean than the normal.
</p>
<p>
</p>
<p>
This might happen because a larger than normal lump of meat is either
included or excluded.
</p>
<p>
</p>
<p>
We first create a <a class="link" href="../../../dist_ref/dists/cauchy_dist.html" title="Cauchy-Lorentz Distribution">Cauchy
Distribution</a> with the original mean and standard deviation,
and estimate the fraction that lie below our minimum weight specification.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">cauchy</span> <span class="identifier">cpacks</span><span class="special">(</span><span class="identifier">mean</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Cauchy Setting the packer to "</span> <span class="special">&lt;&lt;</span> <span class="identifier">mean</span> <span class="special">&lt;&lt;</span> <span class="string">" will mean that "</span>
<span class="special">&lt;&lt;</span> <span class="string">"fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">cpacks</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Cauchy Setting the packer to 3 will mean that fraction of packs &gt;= 2.9 is 0.75</span></pre>
<p>
</p>
<p>
</p>
<p>
Note that far fewer of the packs meet the specification, only 75%
instead of 95%. Now we can repeat the find_location, using the cauchy
distribution as template parameter, in place of the normal used above.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">lc</span> <span class="special">=</span> <span class="identifier">find_location</span><span class="special">&lt;</span><span class="identifier">cauchy</span><span class="special">&gt;(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="identifier">under_fraction</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"find_location&lt;cauchy&gt;(minimum_weight, over fraction, standard_deviation); "</span> <span class="special">&lt;&lt;</span> <span class="identifier">lc</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// find_location&lt;cauchy&gt;(minimum_weight, over fraction, packs.standard_deviation()); 3.53138</span></pre>
<p>
</p>
<p>
</p>
<p>
Note that the safe_mean setting needs to be much higher, 3.53138
instead of 3.06449, so we will make rather less profit.
</p>
<p>
</p>
<p>
And again confirm that the fraction meeting specification is as expected.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">cauchy</span> <span class="identifier">goodcpacks</span><span class="special">(</span><span class="identifier">lc</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Cauchy Setting the packer to "</span> <span class="special">&lt;&lt;</span> <span class="identifier">lc</span> <span class="special">&lt;&lt;</span> <span class="string">" will mean that "</span>
<span class="special">&lt;&lt;</span> <span class="string">"fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">goodcpacks</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Cauchy Setting the packer to 3.53138 will mean that fraction of packs &gt;= 2.9 is 0.95</span></pre>
<p>
</p>
<p>
</p>
<p>
Finally we could estimate the effect of a much tighter specification,
that 99% of packs met the specification.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Cauchy Setting the packer to "</span>
<span class="special">&lt;&lt;</span> <span class="identifier">find_location</span><span class="special">&lt;</span><span class="identifier">cauchy</span><span class="special">&gt;(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="number">0.99</span><span class="special">,</span> <span class="identifier">standard_deviation</span><span class="special">)</span>
<span class="special">&lt;&lt;</span> <span class="string">" will mean that "</span>
<span class="special">&lt;&lt;</span> <span class="string">"fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">goodcpacks</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span></pre>
<p>
</p>
<p>
</p>
<p>
Setting the packer to 3.13263 will mean that fraction of packs &gt;=
2.9 is 0.99, but will more than double the mean loss from 0.0644
to 0.133 kg per pack.
</p>
<p>
</p>
<p>
Of course, this calculation is not limited to packs of meat, it applies
to dispensing anything, and it also applies to a 'virtual' material
like any measurement.
</p>
<p>
</p>
<p>
The only caveat is that the calculation assumes that the standard
deviation (scale) is known with a reasonably low uncertainty, something
that is not so easy to ensure in practice. And that the distribution
is well defined, <a class="link" href="../../../dist_ref/dists/normal_dist.html" title="Normal (Gaussian) Distribution">Normal
Distribution</a> or <a class="link" href="../../../dist_ref/dists/cauchy_dist.html" title="Cauchy-Lorentz Distribution">Cauchy
Distribution</a>, or some other.
</p>
<p>
</p>
<p>
If one is simply dispensing a very large number of packs, then it
may be feasible to measure the weight of hundreds or thousands of
packs. With a healthy 'degrees of freedom', the confidence intervals
for the standard deviation are not too wide, typically about + and
- 10% for hundreds of observations.
</p>
<p>
</p>
<p>
For other applications, where it is more difficult or expensive to
make many observations, the confidence intervals are depressingly
wide.
</p>
<p>
</p>
<p>
See <a class="link" href="../cs_eg/chi_sq_intervals.html" title="Confidence Intervals on the Standard Deviation">Confidence
Intervals on the standard deviation</a> for a worked example
<a href="../../../../../../../../example/chi_square_std_dev_test.cpp" target="_top">chi_square_std_dev_test.cpp</a>
of estimating these intervals.
</p>
<p>
<a name="math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg.changing_the_scale_or_standard_deviation"></a>
</p>
<h5>
<a name="id995060"></a>
<a class="link" href="find_mean_and_sd_eg.html#math_toolkit.dist.stat_tut.weg.find_eg.find_mean_and_sd_eg.changing_the_scale_or_standard_deviation">Changing
the scale or standard deviation</a>
</h5>
<p>
</p>
<p>
Alternatively, we could invest in a better (more precise) packer
(or measuring device) with a lower standard deviation, or scale.
</p>
<p>
</p>
<p>
This might cost more, but would reduce the amount we have to 'give
away' in order to meet the specification.
</p>
<p>
</p>
<p>
To estimate how much better (how much smaller standard deviation)
it would have to be, we need to get the 5% quantile to be located
at the under_weight limit, 2.9
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">p</span> <span class="special">=</span> <span class="number">0.05</span><span class="special">;</span> <span class="comment">// wanted p th quantile.
</span><span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Quantile of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">p</span> <span class="special">&lt;&lt;</span> <span class="string">" = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">quantile</span><span class="special">(</span><span class="identifier">packs</span><span class="special">,</span> <span class="identifier">p</span><span class="special">)</span>
<span class="special">&lt;&lt;</span> <span class="string">", mean = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">packs</span><span class="special">.</span><span class="identifier">mean</span><span class="special">()</span> <span class="special">&lt;&lt;</span> <span class="string">", sd = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">packs</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span></pre>
<p>
</p>
<p>
</p>
<p>
Quantile of 0.05 = 2.83551, mean = 3, sd = 0.1
</p>
<p>
</p>
<p>
With the current packer (mean = 3, sd = 0.1), the 5% quantile is
at 2.8551 kg, a little below our target of 2.9 kg. So we know that
the standard deviation is going to have to be smaller.
</p>
<p>
</p>
<p>
Let's start by guessing that it (now 0.1) needs to be halved, to
a standard deviation of 0.05 kg.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">normal</span> <span class="identifier">pack05</span><span class="special">(</span><span class="identifier">mean</span><span class="special">,</span> <span class="number">0.05</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Quantile of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">p</span> <span class="special">&lt;&lt;</span> <span class="string">" = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">quantile</span><span class="special">(</span><span class="identifier">pack05</span><span class="special">,</span> <span class="identifier">p</span><span class="special">)</span>
<span class="special">&lt;&lt;</span> <span class="string">", mean = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack05</span><span class="special">.</span><span class="identifier">mean</span><span class="special">()</span> <span class="special">&lt;&lt;</span> <span class="string">", sd = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack05</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Quantile of 0.05 = 2.91776, mean = 3, sd = 0.05
</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span><span class="string">"Fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span> <span class="special">&lt;&lt;</span> <span class="string">" with a mean of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">mean</span>
<span class="special">&lt;&lt;</span> <span class="string">" and standard deviation of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack05</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">pack05</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Fraction of packs &gt;= 2.9 with a mean of 3 and standard deviation of 0.05 is 0.97725</span></pre>
<p>
</p>
<p>
</p>
<p>
So 0.05 was quite a good guess, but we are a little over the 2.9
target, so the standard deviation could be a tiny bit more. So we
could do some more guessing to get closer, say by increasing standard
deviation to 0.06 kg, constructing another new distribution called
pack06.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">normal</span> <span class="identifier">pack06</span><span class="special">(</span><span class="identifier">mean</span><span class="special">,</span> <span class="number">0.06</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"Quantile of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">p</span> <span class="special">&lt;&lt;</span> <span class="string">" = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">quantile</span><span class="special">(</span><span class="identifier">pack06</span><span class="special">,</span> <span class="identifier">p</span><span class="special">)</span>
<span class="special">&lt;&lt;</span> <span class="string">", mean = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack06</span><span class="special">.</span><span class="identifier">mean</span><span class="special">()</span> <span class="special">&lt;&lt;</span> <span class="string">", sd = "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack06</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Quantile of 0.05 = 2.90131, mean = 3, sd = 0.06
</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span><span class="string">"Fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span> <span class="special">&lt;&lt;</span> <span class="string">" with a mean of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">mean</span>
<span class="special">&lt;&lt;</span> <span class="string">" and standard deviation of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack06</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">pack06</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Fraction of packs &gt;= 2.9 with a mean of 3 and standard deviation of 0.06 is 0.95221</span></pre>
<p>
</p>
<p>
</p>
<p>
Now we are getting really close, but to do the job properly, we might
need to use root finding method, for example the tools provided,
and used elsewhere, in the Math Toolkit, see <a class="link" href="../../../../toolkit/internals1/roots2.html" title="Root Finding Without Derivatives">Root
Finding Without Derivatives</a>.
</p>
<p>
</p>
<p>
But in this (normal) distribution case, we can and should be even
smarter and make a direct calculation.
</p>
<p>
</p>
<p>
Our required limit is minimum_weight = 2.9 kg, often called the random
variate z. For a standard normal distribution, then probability p
= N((minimum_weight - mean) / sd).
</p>
<p>
</p>
<p>
We want to find the standard deviation that would be required to
meet this limit, so that the p th quantile is located at z (minimum_weight).
In this case, the 0.05 (5%) quantile is at 2.9 kg pack weight, when
the mean is 3 kg, ensuring that 0.95 (95%) of packs are above the
minimum weight.
</p>
<p>
</p>
<p>
Rearranging, we can directly calculate the required standard deviation:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">normal</span> <span class="identifier">N01</span><span class="special">;</span> <span class="comment">// standard normal distribution with meamn zero and unit standard deviation.
</span><span class="identifier">p</span> <span class="special">=</span> <span class="number">0.05</span><span class="special">;</span>
<span class="keyword">double</span> <span class="identifier">qp</span> <span class="special">=</span> <span class="identifier">quantile</span><span class="special">(</span><span class="identifier">N01</span><span class="special">,</span> <span class="identifier">p</span><span class="special">);</span>
<span class="keyword">double</span> <span class="identifier">sd95</span> <span class="special">=</span> <span class="special">(</span><span class="identifier">minimum_weight</span> <span class="special">-</span> <span class="identifier">mean</span><span class="special">)</span> <span class="special">/</span> <span class="identifier">qp</span><span class="special">;</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"For the "</span><span class="special">&lt;&lt;</span> <span class="identifier">p</span> <span class="special">&lt;&lt;</span> <span class="string">"th quantile to be located at "</span>
<span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span> <span class="special">&lt;&lt;</span> <span class="string">", would need a standard deviation of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">sd95</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// For the 0.05th quantile to be located at 2.9, would need a standard deviation of 0.0607957</span></pre>
<p>
</p>
<p>
</p>
<p>
We can now construct a new (normal) distribution pack95 for the 'better'
packer, and check that our distribution will meet the specification.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">normal</span> <span class="identifier">pack95</span><span class="special">(</span><span class="identifier">mean</span><span class="special">,</span> <span class="identifier">sd95</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span><span class="string">"Fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span> <span class="special">&lt;&lt;</span> <span class="string">" with a mean of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">mean</span>
<span class="special">&lt;&lt;</span> <span class="string">" and standard deviation of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack95</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">pack95</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Fraction of packs &gt;= 2.9 with a mean of 3 and standard deviation of 0.0607957 is 0.95</span></pre>
<p>
</p>
<p>
</p>
<p>
This calculation is generalized in the free function find_scale,
as shown below, giving the same standard deviation.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">ss</span> <span class="special">=</span> <span class="identifier">find_scale</span><span class="special">&lt;</span><span class="identifier">normal</span><span class="special">&gt;(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="identifier">under_fraction</span><span class="special">,</span> <span class="identifier">packs</span><span class="special">.</span><span class="identifier">mean</span><span class="special">());</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"find_scale&lt;normal&gt;(minimum_weight, under_fraction, packs.mean()); "</span> <span class="special">&lt;&lt;</span> <span class="identifier">ss</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// find_scale&lt;normal&gt;(minimum_weight, under_fraction, packs.mean()); 0.0607957</span></pre>
<p>
</p>
<p>
</p>
<p>
If we had defined an over_fraction, or percentage that must pass
specification
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">over_fraction</span> <span class="special">=</span> <span class="number">0.95</span><span class="special">;</span></pre>
<p>
</p>
<p>
</p>
<p>
And (wrongly) written
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">sso</span> <span class="special">=</span> <span class="identifier">find_scale</span><span class="special">&lt;</span><span class="identifier">normal</span><span class="special">&gt;(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="identifier">over_fraction</span><span class="special">,</span> <span class="identifier">packs</span><span class="special">.</span><span class="identifier">mean</span><span class="special">());</span>
</pre>
<p>
</p>
<p>
With the default policy, we would get a message like
</p>
<p>
</p>
<pre class="programlisting">Message from thrown exception was:
Error in function boost::math::find_scale&lt;Dist, Policy&gt;(double, double, double, Policy):
Computed scale (-0.060795683191176959) is &lt;= 0! Was the complement intended?
</pre>
<p>
</p>
<p>
But this would return a <span class="bold"><strong>negative</strong></span>
standard deviation - obviously impossible. The probability should
be 1 - over_fraction, not over_fraction, thus:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">ss1o</span> <span class="special">=</span> <span class="identifier">find_scale</span><span class="special">&lt;</span><span class="identifier">normal</span><span class="special">&gt;(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="number">1</span> <span class="special">-</span> <span class="identifier">over_fraction</span><span class="special">,</span> <span class="identifier">packs</span><span class="special">.</span><span class="identifier">mean</span><span class="special">());</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"find_scale&lt;normal&gt;(minimum_weight, under_fraction, packs.mean()); "</span> <span class="special">&lt;&lt;</span> <span class="identifier">ss1o</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// find_scale&lt;normal&gt;(minimum_weight, under_fraction, packs.mean()); 0.0607957</span></pre>
<p>
</p>
<p>
</p>
<p>
But notice that using '1 - over_fraction' - will lead to a <a class="link" href="../../overview/complements.html#why_complements">loss of accuracy, especially if over_fraction
was close to unity.</a> In this (very common) case, we should
instead use the <a class="link" href="../../overview.html#complements">complements</a>, giving
the most accurate result.
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">double</span> <span class="identifier">ssc</span> <span class="special">=</span> <span class="identifier">find_scale</span><span class="special">&lt;</span><span class="identifier">normal</span><span class="special">&gt;(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">minimum_weight</span><span class="special">,</span> <span class="identifier">over_fraction</span><span class="special">,</span> <span class="identifier">packs</span><span class="special">.</span><span class="identifier">mean</span><span class="special">()));</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span> <span class="string">"find_scale&lt;normal&gt;(complement(minimum_weight, over_fraction, packs.mean())); "</span> <span class="special">&lt;&lt;</span> <span class="identifier">ssc</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// find_scale&lt;normal&gt;(complement(minimum_weight, over_fraction, packs.mean())); 0.0607957</span></pre>
<p>
</p>
<p>
</p>
<p>
Note that our guess of 0.06 was close to the accurate value of 0.060795683191176959.
</p>
<p>
</p>
<p>
We can again confirm our prediction thus:
</p>
<p>
</p>
<p>
</p>
<pre class="programlisting"><span class="identifier">normal</span> <span class="identifier">pack95c</span><span class="special">(</span><span class="identifier">mean</span><span class="special">,</span> <span class="identifier">ssc</span><span class="special">);</span>
<span class="identifier">cout</span> <span class="special">&lt;&lt;</span><span class="string">"Fraction of packs &gt;= "</span> <span class="special">&lt;&lt;</span> <span class="identifier">minimum_weight</span> <span class="special">&lt;&lt;</span> <span class="string">" with a mean of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">mean</span>
<span class="special">&lt;&lt;</span> <span class="string">" and standard deviation of "</span> <span class="special">&lt;&lt;</span> <span class="identifier">pack95c</span><span class="special">.</span><span class="identifier">standard_deviation</span><span class="special">()</span>
<span class="special">&lt;&lt;</span> <span class="string">" is "</span> <span class="special">&lt;&lt;</span> <span class="identifier">cdf</span><span class="special">(</span><span class="identifier">complement</span><span class="special">(</span><span class="identifier">pack95c</span><span class="special">,</span> <span class="identifier">minimum_weight</span><span class="special">))</span> <span class="special">&lt;&lt;</span> <span class="identifier">endl</span><span class="special">;</span>
<span class="comment">// Fraction of packs &gt;= 2.9 with a mean of 3 and standard deviation of 0.0607957 is 0.95</span></pre>
<p>
</p>
<p>
</p>
<p>
Notice that these two deceptively simple questions:
</p>
<p>
</p>
<div class="itemizedlist"><ul type="disc"><li>
Do we over-fill to make sure we meet a minimum specification
(or under-fill to avoid an overdose)?
</li></ul></div>
<p>
</p>
<p>
and/or
</p>
<p>
</p>
<div class="itemizedlist"><ul type="disc"><li>
Do we measure better?
</li></ul></div>
<p>
</p>
<p>
are actually extremely common.
</p>
<p>
</p>
<p>
The weight of beef might be replaced by a measurement of more or
less anything, from drug tablet content, Apollo landing rocket firing,
X-ray treatment doses...
</p>
<p>
</p>
<p>
The scale can be variation in dispensing or uncertainty in measurement.
</p>
<p>
See <a href="../../../../../../../../example/find_mean_and_sd_normal.cpp" target="_top">find_mean_and_sd_normal.cpp</a>
for full source code &amp; appended program output.
</p>
</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 &#169; 2006 , 2007, 2008, 2009, 2010 John Maddock, Paul A. Bristow,
Hubert Holin, Xiaogang Zhang, Bruno Lalande, Johan R&#229;de, Gautam Sewani and
Thijs van den Berg<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="find_scale_eg.html"><img src="../../../../../../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../find_eg.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="../nag_library.html"><img src="../../../../../../../../../../doc/src/images/next.png" alt="Next"></a>
</div>
</body>
</html>