<< maokts ARMA and VARMA tools theta2arm2 >>

Grocer >> ARMA and VARMA tools > pacf

pacf

Partial autocorrelation function

CALLING SEQUENCE

[respacf]=pacf(namey,varargin)

PARAMETERS

Input

* namey = a time series, a real (nx1) vector or a string equal to the name of a time series or a (nx1) real vector between quotes

* argi = (optional) string arguments that can be:

  - 'noplt' if the user does not want to plot the partial autocorrelation coefficients

  - 'm=xx' where xx is the number of calculated coefficients (default: floor(size(grocer_y,'*')/4)

  - 'size=xx' where xx is the size of the confidence band (default: 0.05)

 

Output

* respacf = a tlist with

  . respacf('meth')   = 'pacf'

  . respacf('y')      = values of the input variable

  . respacf('pacf')   = partial autocorrelation coeffcients

  . respacf('pacf_l') = low bound of the confidence interval

  . respacf('pacf_u') = upper bound of the confidence interval

  . respacf('size') = size of the confidence band

  . respacf('namey') = name of variable

  . respacf('prests') = %t if variable is a ts

DESCRIPTION

Calculates sample partial autocorrelation coefficients.

EXAMPLE

load(GROCERDIR+'/data/varma_d.dat');
elec_cons = transdif(seriesa,0,1,1,12);respacf=pacf(elec_cons,'m=30')
 
//Calculates the 30 first partial autocorrelations for the index of electricty consumption provided in database varma_d.dat.

AUTHOR

Eric Dubois 2004

Report an issue
<< maokts ARMA and VARMA tools theta2arm2 >>