Kolmogorov-Smirnov test
Purpose
Description
Macro Synopsis
Modules
Related Functions
References
Purpose
Kolmogorov-Smirnov test
Description
Using the K-S-Test, one can determine whether two data sets
are drawn from the same distribution. The function performs a significance test and compares the cumulative distribution functions of the given signals xA and xB, and calculates the maximum distance D between them.
What makes the K-S-test very useful is its invariance under
reparametrization of x, i.e. the x axis can be locally stretched or
shifted without changing D.
The results of "Kolmogorov-Smirnov test", applied to two signals xA and xB, will appear
in the Dataplore ® message window.
Return parameters of "Kolmogorov-Smirnov test" are:
- the maximum distance D
- the significance signif, i.e. the probability [0..1] of randomly equal distributions, where small values indicate significant differences in the cumulative distribution functions.
Macro Synopsis
KSTest([xA,xB],&D,&signif);
signal xA,xB;
float D,signif;
Modules
Statistics
Related Functions
BDS test, Test for different histograms,
Test for different means, Test for different variances,
Test for non-normal-distributed data,
Test for non-white-noise,
Test for the mean of a Gaussian, Test for the variance of a Gaussian,
Wilcoxon test
References
Hollander/Wolfe [13], Lehmann [36]