I tried to specify a model in dse1 but something isn't right. Anybody
have any tips?
model<-SS(F=f,G=g,H=h,Q=q,z0=z,P0=p)
Error in locateSS(model$R, constants$R, "R", p, p, plist) :
The dimension of something in the SS model structure is bad.
> dim(f)
[1] 5 5
> dim(g)
[1] 5 1
> dim(h)
[1] 1 5
I thought that I wanted the non-innovations form but wanted R and w(t) to be
zero. I
thought leaving out R would give that. What I'm trying to do is estimate a
transfer function
noise model. I noticed that you suggested to another person to use ARMA()
and one can estimate the forecast function of
I reworked this using the innovations form and it seems to work. But none of
the parameters were changed after estimation.
summary lists:
$counts
function gradient
1 1
It guess it calculates the function but doesn't optimize the parameters.
I just used: tfn.est <- estMaxLik(
Greetings:
I recently installed R 2.11.1 for windows. It seems that there is only
online help now. Is there any way to get the local docs? I don't have
always-on high-speed internet.
thanks,
Bob
--
View this message in context:
http://r.789695.n4.nabble.com/online-documentation-only-tp2400647
Thanks for the replies. I tried help.start() and ?foo but my browser opened
and was blank. It just said can't open site as I was offline. Must be my
system. I'll try again. Maybe I can get it sorted out. Maybe the install was
bad.
Thanks again,
Bob
--
View this message in context:
http://r.789
The problem was I needed to "connect" even though I was offline and couldn't
get online. In this case, "connect" apparently means to start the loopback
device. After doing this, the docs work!
Must be a quirk of win 7. Thanks for all the replies.
Bob
--
View this message in context:
http://r
Greetings:
I'm trying to install R-base on Suse 10.3 but Yast complains of failed
dependancies. It needs blas and readline. I installed readline and gsl thinking
that gsl would solve the blas prob, but no luck. The readline problem remains
as well.
Any ideas??
Thanks,
Bob
---
Found it!
http://download.opensuse.org/distribution/10.3/repo/oss/suse/i586/
Consider adding this link to a readme file in the download directory.
Bob
bob mccall <[EMAIL PROTECTED]> wrote: Greetings:
I'm trying to install R-base on Suse 10.3 but Yast complains of failed
depen
Look in the package "forecast" for the function "Arima". It will do what you
want. It's different than arima function in the stats package.
Bob
Pele wrote:
>
> Hi R users,
>
> I am doing cross correlation analysis on 2 time series (call them
> y-series and x-series) where I need the use the mo
9 matches
Mail list logo