Message-ID: <alpine.LRH.1.00.0808290129150.28720@stat12.stat.auckland.ac.nz>
Date: 2008-08-28T13:34:13Z
From: David Scott
Subject: Plots spanning columns
In-Reply-To: <48B69CC8.1070803@decsai.ugr.es>
On Thu, 28 Aug 2008, Jose Luis Aznarte M. wrote:
> Hi! I want to plot three graphs (residuals, ACF and PACF of a model).
> Ideally I would use a c(2,2) disposition where the residuals plot would start
> at position 1,1 and span to position 1,2. Then I would plot the ACF in
> position 2,1 and the PACF in position 2,2. Maybe is clearer like this:
>
> --------------------------
> | |
> | residuals |
> | |
> --------------------------
> ------------ -------------
> | | | |
> | ACF | | PACF |
> | | | |
> ------------ -------------
>
> Does anyone know if that is possible at all? Cheers!
>
I happened to do virtually that plot just recently. Just had data rather
than residuals:
### Function to display plot, ACF and PACF
displayTimeSeries <- function(x, heading = NULL,
heights = NULL, ...){
defaultPars <- par(no.readonly = TRUE)
if (is.null(heading)) {
heading <- paste("Series: ", deparse(substitute(x)))
}
if (is.null(heights)) heights <- c(1,1)
layout(matrix(c(1,1,2,3), 2, 2, byrow = TRUE), heights = heights)
plot(x, main = heading)
par(mar = c(5,4,1,2) + 0.1)
acfVal <- acf(x, main = "")$acf
pacfVal <- acf(x, type = "partial", main = "")$acf
par(defaultPars)
invisible(list(acf = acfVal, pacf = pacfVal))
}
If you add a line which calculates the residuals and plots them instead of
the data, then you should have what you want.
David Scott
_________________________________________________________________
David Scott Department of Statistics, Tamaki Campus
The University of Auckland, PB 92019
Auckland 1142, NEW ZEALAND
Phone: +64 9 373 7599 ext 86830 Fax: +64 9 373 7000
Email: d.scott at auckland.ac.nz
Graduate Officer, Department of Statistics
Director of Consulting, Department of Statistics