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] abvq_v1_0.gz(3 Kbytes)
Manuscript Title: SMOOS: a program for the filtration of non-stationary statistical series.
Authors: V.B. Zlokazov
Program title: SMOOS,SMOSI
Catalogue identifier: ABVQ_v1_0
Distribution format: gz
Journal reference: Comput. Phys. Commun. 21(1981)373
Programming language: Fortran.
Computer: CDC-6500.
Operating system: SCOPE.
RAM: 1K words
Word size: 60
Keywords: General purpose, Statistical methods, Statistical series, Non-stationary trend, Numerical filter, Difference equation, Filtration, Programming, Data analysis.
Classification: 4.13.

Nature of problem:
The program either smoothes a statistical series with a strongly non- stationary (e.g. resonance-like) trend or extracts from it a low frequency envelope from below.

Solution method:
The high and low frequency filters sought for, are constructed as solutions of the problem of minimization of oscillation or variability measures and distances of the functions from the initial series. The resulting difference equations are solved by a method, which is fast and compact with respect to the computer memory.


Running time:
0.2 s for a series of 100 numbers.