ARMA model fitting
in [Matlab]
|
From: Abdullah M. Hafiz on 1 Feb 2010 00:11 Thanks Rajiv and Wayne for your kind suggestion. I need something to know about 'resid' command. I'm using it like this: d= resid (arma_model, DAT, 'corr'); plot (d); The plots return the autocorrelation of error and cross correlation between the error and the input. I'm wondering is there any way I can plot the autocorrelation of the residuals in normalized form (in a scale of y between 0 to 1)? "Rajiv Singh" <Rajiv.SinghNoSpam(a)mathworks.com> wrote in message <hjvj3e$a94$1(a)fred.mathworks.com>... > Look up functions RESID, COMPARE, PREDICT and PE (in System Identification > Toolbox). In particular, RESID will plot the autocorrelation of residuals. > > Rajiv > > "Abdullah M. Hafiz" <hafiz_fcc(a)yahoo.com> wrote in message > news:hjqvlb$3h9$1(a)fred.mathworks.com... > > Hi, > > I've been working in developing input/output ARMA model for surface > > roughness profile. I am using MATLAB armax command for that, which has a > > flexibility to choose my model's order. I was just wondering, is there any > > way I can plot the residuals, obtained from the ARMA model. My intension > > is to verify the adequacy of the developed model, that's why thinking to > > figure out the aucorrelation function of residuals. But I'm really > > confused regarding how to do that. > > It would also be great, if someone states other ways to verify the model > > adequacy developed by armax. > > I would also prefer some other ways to develop ARMA model as well as test > > its adequacy. > > > > Regards, > > > > Hafiz > > >
From: Rajiv Singh on 2 Feb 2010 17:15
The autocorrelation is indeed scaled. Its value at zero lag should be 1 and for non-zero lags a value between 0 and 1. If you want to get your hands at the raw prediction error data, you can obtain it from the data object d, as e = d.y. Rajiv "Abdullah M. Hafiz" <hafiz_fcc(a)yahoo.com> wrote in message news:hk5np8$21n$1(a)fred.mathworks.com... > Thanks Rajiv and Wayne for your kind suggestion. > I need something to know about 'resid' command. I'm using it like this: > > d= resid (arma_model, DAT, 'corr'); plot (d); > > The plots return the autocorrelation of error and cross correlation > between the error and the input. I'm wondering is there any way I can plot > the autocorrelation of the residuals in normalized form (in a scale of y > between 0 to 1)? > "Rajiv Singh" <Rajiv.SinghNoSpam(a)mathworks.com> wrote in message > <hjvj3e$a94$1(a)fred.mathworks.com>... >> Look up functions RESID, COMPARE, PREDICT and PE (in System >> Identification Toolbox). In particular, RESID will plot the >> autocorrelation of residuals. >> >> Rajiv >> >> "Abdullah M. Hafiz" <hafiz_fcc(a)yahoo.com> wrote in message >> news:hjqvlb$3h9$1(a)fred.mathworks.com... >> > Hi, >> > I've been working in developing input/output ARMA model for surface >> > roughness profile. I am using MATLAB armax command for that, which has >> > a flexibility to choose my model's order. I was just wondering, is >> > there any way I can plot the residuals, obtained from the ARMA model. >> > My intension is to verify the adequacy of the developed model, that's >> > why thinking to figure out the aucorrelation function of residuals. But >> > I'm really confused regarding how to do that. >> > It would also be great, if someone states other ways to verify the >> > model adequacy developed by armax. >> > I would also prefer some other ways to develop ARMA model as well as >> > test its adequacy. >> > >> > Regards, >> > >> > Hafiz >> > >> |