Difference between revisions of "Pooled standard deviation"
(Forced creation of a TOC - this will improve the formatting on the main page 'Did you know...' section.) |
(Fix for the symbols and maths - all $x$ usage has been replaced by <math> tags or direct HTML conversion.) |
||
| Line 6: | Line 6: | ||
A problem often arises when the combination of several series of measurements performed under similar conditions | A problem often arises when the combination of several series of measurements performed under similar conditions | ||
is desired to achieve an improved estimate of the imprecision of the process. If it can be assumed that all the | is desired to achieve an improved estimate of the imprecision of the process. If it can be assumed that all the | ||
| − | series are of the same precision although their means may differ, the pooled standard deviations | + | series are of the same precision although their means may differ, the pooled standard deviations ''s<sub>p</sub>'' |
| − | from | + | from ''k'' series of measurements can be calculated as |
| − | + | ||
| + | <math> | ||
s_p=\sqrt{\frac{(n_1-1)s_1^2+(n_2-1)s_2^2+...+(n_k-1)s_k^2}{n_1+n_2+...+n_k-k}} | s_p=\sqrt{\frac{(n_1-1)s_1^2+(n_2-1)s_2^2+...+(n_k-1)s_k^2}{n_1+n_2+...+n_k-k}} | ||
| − | + | </math> | |
| − | The suffices | + | |
| − | + | ||
| + | The suffices ''1, 2, ..., k'' refer to the different series of measurements. In this case it is assumed that there exists a single underlying standard deviation ''σ'' of which the pooled standard deviation ''s<sub>p</sub>'' is a better estimate than the individual calculated standard deviations ''s<sub>1</sub>, s<sub>2</sub>, ..., s<sub>k</sub>'', For the special case where ''k'' sets of duplicate measurements are available, the above equation reduces to | ||
| + | |||
| + | <math> | ||
s_p=\sqrt{\frac{\sum(x_{i1}-x_{i2})^2}{2k}} | s_p=\sqrt{\frac{\sum(x_{i1}-x_{i2})^2}{2k}} | ||
| − | + | </math> | |
| − | Results from various series of measurements can be combined in the following way to give a pooled relative standard deviation | + | |
| − | + | Results from various series of measurements can be combined in the following way to give a pooled relative standard deviation ''s<sub>r,p</sub>'': | |
| + | |||
| + | <math> | ||
s_{r,p}=\sqrt{\frac{\sum(n_i-1)s_{r,i}^2}{\sum n_i -1}} = \sqrt{\frac{\sum(n_i-1)s_i^2x_i^{-2}}{\sum n_i -1}} | s_{r,p}=\sqrt{\frac{\sum(n_i-1)s_{r,i}^2}{\sum n_i -1}} = \sqrt{\frac{\sum(n_i-1)s_i^2x_i^{-2}}{\sum n_i -1}} | ||
| − | + | </math> | |
Revision as of 14:35, 3 November 2015
Contents
IUPAC - pooled standard deviation
IUPAC :pooled standard deviation
A problem often arises when the combination of several series of measurements performed under similar conditions is desired to achieve an improved estimate of the imprecision of the process. If it can be assumed that all the series are of the same precision although their means may differ, the pooled standard deviations sp from k series of measurements can be calculated as
[math] s_p=\sqrt{\frac{(n_1-1)s_1^2+(n_2-1)s_2^2+...+(n_k-1)s_k^2}{n_1+n_2+...+n_k-k}} [/math]
The suffices 1, 2, ..., k refer to the different series of measurements. In this case it is assumed that there exists a single underlying standard deviation σ of which the pooled standard deviation sp is a better estimate than the individual calculated standard deviations s1, s2, ..., sk, For the special case where k sets of duplicate measurements are available, the above equation reduces to
[math] s_p=\sqrt{\frac{\sum(x_{i1}-x_{i2})^2}{2k}} [/math]
Results from various series of measurements can be combined in the following way to give a pooled relative standard deviation sr,p:
[math] s_{r,p}=\sqrt{\frac{\sum(n_i-1)s_{r,i}^2}{\sum n_i -1}} = \sqrt{\frac{\sum(n_i-1)s_i^2x_i^{-2}}{\sum n_i -1}} [/math]
