Programmer Guide/Command Reference/EVAL/var: Difference between revisions
From STX Wiki
< Programmer Guide | Command Reference | EVAL
Jump to navigationJump to search
No edit summary |
No edit summary |
||
| Line 15: | Line 15: | ||
;Result 3: CompuThe covariance matrix ''v'' of the column vectors of ''x''. | ;Result 3: CompuThe covariance matrix ''v'' of the column vectors of ''x''. | ||
:<code>''v<sub>i,j</sub>'' = sum<sub>k = 0..nrow(''x'')</sub> ( (x<sub>k,i</sub>-a<sub>i</sub>) * (x<sub>k,j</sub>-a<sub>j</sub>) ) / (ncol(''x'')-1) , with: i,j = 0..ncol(''x'')</code> | :<code>''v<sub>i,j</sub>'' = sum<sub>k = 0..nrow(''x'')</sub> ( (x<sub>k,i</sub>-a<sub>i</sub>) * (x<sub>k,j</sub>-a<sub>j</sub>) ) / (ncol(''x'')-1) , with: i,j = 0..ncol(''x'')</code> | ||
:The column averages a<sub>i=0..ncol(''x'') are computed as follows: | :The column averages a<sub>i=0..ncol(''x'')</sub> are computed as follows: | ||
:{|class="einrahmen" | ::{|class="einrahmen" | ||
|''y'' not supplied || | |''y'' not supplied || a<sub>i</sub> = avr(''x''<sub>*,i</sub>) | ||
|- | |- | ||
|''y''<sub>scalar</sub> || | |''y''<sub>scalar</sub> || a<sub>i</sub> = ''y'' | ||
|- | |- | ||
|''y''<sub>vector</sub> || | |''y''<sub>vector</sub> || a<sub>i</sub> = ''y''<sub>i</sub> | ||
|- | |- | ||
|} | |} | ||
;See also: [[Programmer_Guide/Command_Reference/EVAL/avr|avr]], [[Programmer_Guide/Command_Reference/EVAL/dev|dev]], [[Programmer_Guide/Command_Reference/EVAL/corr|corr]] | |||
[[Programmer_Guide/Command_Reference/EVAL#Functions|<function list>]] | |||
Revision as of 13:31, 8 April 2011
Compute the variance, covariance or covariance-matrix.
- Usage 1
var(xvector)- Result 1
- The variance v of vector x.
v = sumi = 0..ncol(x)-1 ( (xi-avr(x))^2 ) / (ncol(x)-1)
- Usage 2
var(xvector, yvector)- Result 2
- The covariance v of the vectors x and y.
v = sumi = 0..ncol(x) ( (xi-avr(x)) * (yi-avr(y)) ) / (ncol(x)-1)
- Usage 3
var(xmatrix)var(xmatrix, yscalar)var(xmatrix, yvector)- Result 3
- CompuThe covariance matrix v of the column vectors of x.
vi,j = sumk = 0..nrow(x) ( (xk,i-ai) * (xk,j-aj) ) / (ncol(x)-1) , with: i,j = 0..ncol(x)- The column averages ai=0..ncol(x) are computed as follows:
y not supplied ai = avr(x*,i) yscalar ai = y yvector ai = yi
