Welcome to the L3 Harris Geospatial documentation center. Here you will find reference guides and help documents.
﻿

KUIPERTWO

KUIPERTWO

## Purpose

Compute the two-sided Kuiper statistic (invariant Kolmogorov-Smirnov)

## Explanation

Returns the Kuiper statistic and associated probability
that two arrays of data values are drawn from the same distribution
Algorithm adapted from KSTWO in "Numerical
Recipes" by Press et al., 2nd edition (1992), Chapter 14

## Calling Sequence

kuipertwo, data1, data2, D, prob, [ /PLOT ]

## Input Parameters

data1 - vector of data values, at least 4 data values must be included
for the Kuiper statistic to be meaningful
data2 - second set of data values, does not need to have the same
number of elements as data1

## Output Parameters

D - floating scalar giving the Kuiper statistic. It
specifies the sum of positive and negative deviations between
the cumulative distributions of the two data sets
prob - floating scalar between 0 and 1 giving the significance level of
the Kuiper statistic. Small values of PROB show that the
cumulative distribution function of DATA1 is significantly
different from DATA2

## Optional Input Keyword

/PLOT - If this keyword is set and non-zero, then KUIPERTWO will display
a plot of the CDF of the two data sets.
The data values where the Kuiper statistic is
computed (i.e. at the maximum difference between the CDF of
the two data sets) are indicated by vertical dashed lines.
KUIPERTWO accepts the _EXTRA keyword, so that most plot keywords
(e.g. TITLE, XTITLE, XSTYLE) can also be passed to KUIPERTWO.
/WINDOW - If set the plot to a resizeable graphics window.

## Example

Test whether two vectors created by the RANDOMN function likely came
from the same distribution
IDL> data1 = randomn(seed,40) ;Create data vectors to be
IDL> data2 = randomn(seed,70) ;compared
IDL> kuipertwo, data1, data2, D, prob & print,D,prob

## Procedure Calls

procedure PROB_KUIPER - computes significance of Kuiper distribution

## Revision History

Written W. Landsman August, 1992
FP computation of N_eff H. Ebeling/W. Landsman March 1996
Fix for arrays containing equal values J. Ballet/W. Landsman
Oct. 2001