Mean, Variance, and Standard Deviation
Consider some physical system
. Suppose that a measurement of a particular physical property of this
system,
, can result in one of
distinct outcomes. Let outcome
be associated with
taking the value
. Consider an ensemble of
systems that are identical to system
. Let
be the number of systems in the ensemble that exhibit the outcome
. The mean value of
is, by definition, the average of a very large number of measurements of
. In other words,
![$\displaystyle \langle x\rangle = ~_{\lim N\rightarrow\infty} \sum_{r =1,R}\frac{N_r\,x_r}{N},$](img3414.png) |
(5.20) |
which implies that
![$\displaystyle \langle x\rangle = \sum_{r=1,R}P_r\,x_r,$](img3415.png) |
(5.21) |
where use has been made of Equation (5.1).
Let
![$\displaystyle {\mit\Delta}x = x - \langle x\rangle$](img3416.png) |
(5.22) |
measure the deviation of an individual measurement of
from the mean value. Obviously,
![$\displaystyle \langle{\mit\Delta}x\rangle = \langle x\rangle -\langle\langle x\rangle\rangle = \langle x\rangle -\langle x\rangle =0.$](img3417.png) |
(5.23) |
In other words, the mean deviation from the mean value is zero.
Consider
. This quantity, which is known as the variance of
, is positive definite.
It can only take the value 0 if all measurement of
result in the mean value. Thus, the variance of
measures the degree of scatter about the mean value.
It follows that
![$\displaystyle \left\langle({\mit\Delta} x)^2\right\rangle=\left\langle \left(x ...
...angle=\left\langle x^2\right\rangle - 2\,\langle x\rangle^2+\langle x\rangle^2,$](img3419.png) |
(5.24) |
or
![$\displaystyle \left\langle({\mit\Delta} x)^2\right\rangle= \left\langle x^2\right\rangle -\langle x\rangle^2.$](img3420.png) |
(5.25) |
Finally, the quantity
![$\displaystyle \sigma_x =\left[ \left\langle({\mit\Delta} x)^2\right\rangle\right]^{1/2}$](img3421.png) |
(5.26) |
is known as the standard deviation of
.
The
standard deviation is essentially the width of the range of probable values over which
is distributed around its mean value,
.