README
No OneTemporary
Actions

Size

1 KB

Subscribers

None

README
View Options


	The Kolmogorov-Smirnov test statistic D_n is defined by

	D_n = sup_x \|F(x) - S_n(x)\|

	where n is the sample size, F(x) is a completely specified theoretical
	distribution, and S_n(x) is an empirical distribution function.

	This package defines two functions placed in the namespace "kstest".
	The function

	double KScdf(unsigned n, double x);

	computes the cumulative probability P[D_n <= x] of the 2-sided
	1-sample Kolmogorov-Smirnov distribution with sample size n at x.
	It returns at least 13 decimal digits of precision for n <= 500,
	at least 7 decimal digits of precision for 500 < n <= 100000,
	and a few correct decimal digits for n > 100000.

	The function

	double KSfbar(unsigned n, double x);

	computes the complementary cumulative probability P[D_n > x] of the
	2-sided 1-sample Kolmogorov-Smirnov distribution with sample size n at x.
	It returns at least 10 decimal digits of precision for n <= 500,
	at least 6 decimal digits of precision for 500 < n <= 200000,
	and a few correct decimal digits for n > 200000.

	The program "kscalc" in the "examples" directory takes values of n and x
	from the command line and prints the values returned by "KScdf" and "KSfbar"
	to the standard output.

	If you find this software useful, please cite

	@article{tSIM11a,
	author = {R. Simard and P. L'Ecuyer},
	title = {Computing the Two-Sided {Kolmogorov-Smirnov} Distribution},
	journal = {Journal of Statistical Software},
	volume = {39},
	number = {11},
	note = {URL is \url{http://www.jstatsoft.org/v39/i11}},
	OPTpages = {1--18},
	year = {2011}
	}