Scilab Home page | Wiki | Bug tracker | Forge | Mailing list archives | ATOMS | File exchange
Please login or create an account
Change language to: English - Português - Русский - 日本語

Please note that the recommended version of Scilab is 6.0.0. This page might be outdated.
See the recommended documentation of this function

Aide de Scilab >> Traitement du Signal > filters > lev

lev

Yule-Walker equations (Levinson's algorithm)

Calling Sequence

[ar, sigma2, rc]=lev(r)

Arguments

r

correlation coefficients

ar

auto-Regressive model parameters

sigma2

scale constant

rc

reflection coefficients

Description

This function resolves the Yule-Walker equations using Levinson's algorithm. Generally, it is used to estimate the coefficients of an autoregressive process.

Example

b=1; //numerator
a=[1 -0.7 0.8]; //denominator
x=[1 zeros(1,99)]; //input=impulse
data=filter(b,a,x); //real data
a2=lev(data); //modelized data
a2=a2/a2(1); //normalization
m_data=filter(1,a2,x);
// Compare real data and modelized data
plot(data,"color","blue","lineStyle","none","marker","d");
plot(m_data,"color","red","lineStyle","none","marker","d");
Scilab Enterprises
Copyright (c) 2011-2017 (Scilab Enterprises)
Copyright (c) 1989-2012 (INRIA)
Copyright (c) 1989-2007 (ENPC)
with contributors
Last updated:
Thu Oct 02 13:54:32 CEST 2014