Difference between revisions of "Standard deviation"
m |
RyanMatthews (talk | contribs) (Additions) |
||
| Line 18: | Line 18: | ||
which is the formula for a [[point estimate]] of the true standard deviation from a sample size of ''n''. As such this [[statistical estimator]] itself has a variance which, as the formula indicates, decreases as the sample size increases. | which is the formula for a [[point estimate]] of the true standard deviation from a sample size of ''n''. As such this [[statistical estimator]] itself has a variance which, as the formula indicates, decreases as the sample size increases. | ||
| + | |||
| + | It may be important to consider the standard deviation is but ''a'' measure of dispersion, and not the only one. For instance, a [[Cauchy distribution]] has an undefined standard deviation (or mean), yet a glance at its [[Probability density function | pdf]] suggests that it is not "infinitely" dispersed. | ||
Revision as of 16:45, November 14, 2009
| <math>\frac{d}{dx} \sin x=?\,</math> | This article/section deals with mathematical concepts appropriate for late high school or early college. |
Standard deviation is a measure in statistics of the dispersion of a set of values (represented as <math>X</math>). It is defined as the square root of the variance of these values, where variance is defined as
- <math>\sigma^2 = \operatorname{E}[(X-\operatorname{E}[X])^2] = \operatorname{E}[X^2] - (\operatorname{E}[X])^2</math>
where the expected value of X is E(X).
Thus the standard deviation is
- <math>\sigma = \sqrt{\operatorname{E}[(X-\operatorname{E}[X])^2]} = \sqrt{\operatorname{E}[X^2] - (\operatorname{E}[X])^2}</math>
The formula for standard deviation must not be confused with the formula
- <math>S_{n} = \sqrt {\sum_n(X_n - \bar X)^2 \over n - 1}</math>
(where <math>\bar X = {\sum_n X_n \over N}</math> is the sample mean).
which is the formula for a point estimate of the true standard deviation from a sample size of n. As such this statistical estimator itself has a variance which, as the formula indicates, decreases as the sample size increases.
It may be important to consider the standard deviation is but a measure of dispersion, and not the only one. For instance, a Cauchy distribution has an undefined standard deviation (or mean), yet a glance at its pdf suggests that it is not "infinitely" dispersed.