<?xml version="1.0" encoding="utf-8"?>
<!DOCTYPE document PUBLIC "-//CNX//DTD CNXML 0.5//EN" "http://cnx.rice.edu/technology/cnxml/schema/dtd/0.5/cnxml_plain.dtd">
<document xmlns="http://cnx.rice.edu/cnxml" xmlns:md="http://cnx.rice.edu/mdml/0.4" xmlns:bib="http://bibtexml.sf.net/" id="id33910690">
<name>What is variance?</name>
<metadata>
  <md:version>1.1</md:version>
  <md:created>2006/02/15 04:47:25.092 US/Central</md:created>
  <md:revised>2006/02/15 04:52:35.817 US/Central</md:revised>
  <md:authorlist>
      <md:author id="Brandon_Hodgson">
      <md:firstname>Brandon</md:firstname>
      
      <md:surname>Hodgson</md:surname>
      <md:email>brandon.hodgson@gmail.com</md:email>
    </md:author>
  </md:authorlist>

  <md:maintainerlist>
    <md:maintainer id="Brandon_Hodgson">
      <md:firstname>Brandon</md:firstname>
      
      <md:surname>Hodgson</md:surname>
      <md:email>brandon.hodgson@gmail.com</md:email>
    </md:maintainer>
  </md:maintainerlist>
  
  <md:keywordlist>
    <md:keyword>elen5007</md:keyword>
  </md:keywordlist>

  <md:abstract/>
</metadata>
<content>
<section id="id33878956">
<name>What is variance?</name>
<para id="id33861846">The variance of a random variable is a
measure of its statistical dispersion, indicating how far from the
expected value its values typically are (Wikipedia 2006). The
variance of a real-valued random variable is its second central
moment, and it also happens to be its second cumulant (Wikipedia
2006). The variance of a random variable is the square of its
standard deviation (Wikipedia 2006).</para>
<para id="id33977145">Variance is defined as</para>
<para id="id33852864">
<figure id="id33852870">
<media type="image/png" src="19e027b78a4e0847ce748640ea3fcb13"/>
</figure>(1)(Wikipedia 2006)</para>
<para id="id33861664">if μ = E(X), where E(X) is the expected value
(mean) of the random variable X (Wikipedia 2006). That is, it is
the expected value of the square of the deviation of X from its own
mean (Wikipedia 2006). In plain language, it can be expressed as
"The average of the square of the distance of each data point from
the mean", thus it is the mean squared deviation (Wikipedia 2006).
The variance of random variable X is typically designated as 
<figure id="id33861707">
<media type="image/png" src="3bf48fc8ab2b0bdecb49335acd09afa8"/>
</figure>, 
<figure id="id33870689">
<media type="image/png" src="58a7152a4368bfcf08f1afead3b9514e"/>
</figure>, or simply σ2 (Wikipedia 2006).</para>
<para id="id33870725">This definition of variance can be used for
both discrete and continuous random variables (Wikipedia
2006).</para>
<para id="id33870731">Many distributions, such as the Cauchy
distribution, do not have a variance because the relevant integral
diverges (Wikipedia 2006). In particular, if a distribution does
not have expected value, it does not have variance either
(Wikipedia 2006). The opposite is not true: there are distributions
for which expected value exists, but variance does not (Wikipedia
2006).</para>
<para id="id33870742">Variance will never be negative, provided it
is defined, because the squares are positive or zero (Wikipedia
2006). The unit of variance is the square of the unit of
observation (Wikipedia 2006). Example: The variance of a set of
heights measured in centimeters will be given in square
centimeters. This is an inconveinient result, and so the standard
deviation is generally used (Wikipedia 2006). The standard
deviation is the square root of the variance (Wikipedia
2006).</para>
<para id="id33870766">It can be proven easily from the definition
that the variance does not depend on the mean value μ (Wikipedia
2006). That is, if the variable is "displaced" an amount b by
taking X+b, the variance of the resulting random variable is left
untouched (Wikipedia 2006). By contrast, if the variable is
multiplied by a scaling factor a, the variance is multiplied by a2
(Wikipedia 2006). More formally, if a and b are real constants and
X is a random variable whose variance is defined,</para>
<para id="id33870829">
<figure id="id33870832">
<media type="image/png" src="e7d4ba661fb1d022562314543935e3cb"/>
</figure>(2)(Wikipedia 2006)</para>
<para id="id33879512">Another formula for the variance that follows
in a straightforward manner from the linearity of expected values
and the above definition is:</para>
<para id="id33879519">
<figure id="id33879522">
<media type="image/png" src="dabe8c0d79a42bdb56e7f9a596cda5cd"/>
</figure>(3)(Wikipedia 2006)</para>
<para id="id33879548">This is often used to calculate the variance
in practice (Wikipedia 2006).</para>
<para id="id33879554">One reason for the use of the variance in
preference to other measures of dispersion is that the variance of
the sum (or the difference) of independent random variables is the
sum of their variances (Wikipedia 2006).</para>
<para id="id33879562">Exercise: Why is variance sometimes called
moments of probability distributions? 
<link src="file:///C:/Documents%20and%20Settings/Barney1/My%20Documents/Wits2006/Teletraffic%20engineering/Assignment%202/Html%20files/AnswerVariance.htm">
Answer.</link></para>
<para id="id33879585">References:Wikipedia. "Variance", Wikimedia
Foundation Inc, 
<link src="http://en.wikipedia.org/wiki/Variance">
http://en.wikipedia.org/wiki/Variance</link>, Last accessed 14
February 2006.</para>
<para id="id33879612"/>
<para id="id33879630">Brandon Hodgson</para>
</section>
</content>
</document>
