On Mon, 2 May 2011, Michael Bach wrote:
Uwe Ligges <ligges at statistik.tu-dortmund.de> writes:
On 29.04.2011 17:10, Michael Bach wrote:
Dear R Users,
I am doing stats::decompose() on 4 different time series. When I issue
csdA<- decompose(tsA)
plot(csdA)
I get a summary plot for observed, trend, seasonal and random components
of decomposed time series tsA. As I understand it, the object returned
by decompose() has it's own plot method where mfrow(4,1) etc. is
defined. Now suppose I wanted to wrap those mfrow(4,1) into my own
mfrow(2,2) layout. How could I achieve this? Is there a general way to
handle these cases? Something like a "meta" par(mfrow())?
This does not work and is one of the reasons why the grid package was developed.
Does this mean that there is no way whatsoever or that there is a
workaround via the grid package??
See the gridBase package.