Elsevier Science Home
Computer Physics Communications Program Library
Full text online from Science Direct
Programs in Physics & Physical Chemistry
CPC Home

[Licence| Download | New Version Template] acxb_v1_0.gz(14 Kbytes)
Manuscript Title: Algorithms for the Kac and Renyi tests.
Authors: J.M.F. Chamayou
Program title: RENYIF, RENYIT, TESKAC
Catalogue identifier: ACXB_v1_0
Distribution format: gz
Journal reference: Comput. Phys. Commun. 12(1976)173
Programming language: Fortran.
Computer: CDC 7600.
Operating system: CDC SCOPE.
RAM: 10K words
Word size: 60
Keywords: General purpose, Statistics, Fitting, Asymptotic Renyi distribution, Renyi test, Random size sample test, Kac test.
Classification: 4.9.

Nature of problem:
Given a sample (with fixed size for the Renyi test and random size for the kac test) of independent observations of a random variable having an unknown continuous distribution function G(x). The hypothesis G(x) = F(x) for a given F(x) is tested using the empirical distribution function.

Solution method:
The observations are ranked in increasing order to calculate the empirical distribution function. The maximum of the absolute difference between F(x) and the empirical distribution function is computed and the test of the hypothesis is performed using the asymptotic Renyi distribution.

Restrictions:
The size of the sample must be large enough to allow a valid use of the asymptotic Renyi distribution.

Running time:
Depends on the size of the sample and on the algorithm used to rank the observations in increasing order.