arima/fixed

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

arima/fixed

Nasia Petsa
Dear all,

I have the following problem with determining the argument fixed in arima function. What is the length  of argument fixed for an ARIMA(1,0,0)(0,1,1) and what is the correct  order for the parameters ?

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: arima/fixed

Rolf Turner

On Fri, 29 Jan 2021 12:47:25 +0000
Nasia Petsa <[hidden email]> wrote:

> Dear all,
>
> I have the following problem with determining the argument fixed in
> arima function. What is the length  of argument fixed for an
> ARIMA(1,0,0)(0,1,1) and what is the correct  order for the parameters

Hmm.  The help is indeed pretty opaque, isn't it?  I tried
the following:

set.seed(42)
x <- rnorm(300)
f1 <- arima(x,order=c(1,0,0),seasonal=list(order=c(0,1,1),period=6))
coef(f1) # Which gave:
>        ar1       sma1
> -0.0169276 -0.9999999

f2 <- arima(x,order=c(1,0,0),seasonal=list(order=c(0,1,1),period=6),
            fixed=c(-0.5,NA),transform.pars=FALSE)
coef(f2) # Which gave:
> ar1 sma1
> -0.5 -1.0

So this looks like it's doing the right thing .... ???

Printing f2 indicates that the standard error of "ar1" is 0, which
makes sense since it's fixed.

I hope this helps.  Perhaps someone who actually knows what they are
talking about will chime in.

cheers,

Rolf Turner

--
Honorary Research Fellow
Department of Statistics
University of Auckland
Phone: +64-9-373-7599 ext. 88276

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: arima/fixed

Martin Maechler
>>>>> Rolf Turner
>>>>>     on Sat, 30 Jan 2021 16:11:32 +1300 writes:

    > On Fri, 29 Jan 2021 12:47:25 +0000
    > Nasia Petsa <[hidden email]> wrote:

    >> Dear all,
    >>
    >> I have the following problem with determining the argument fixed in
    >> arima function. What is the length  of argument fixed for an
    >> ARIMA(1,0,0)(0,1,1) and what is the correct  order for the parameters

    > Hmm.  The help is indeed pretty opaque, isn't it?  

Can you propose improvements?

Here(*) is the source code of the help page

  http://svn.r-project.org/R/trunk/src/library/stats/man/arima.Rd

We (and future R users) would be glad for less opaque (and still
concise) wording, notably in simple enough English for the 90%
non-natively English speaking R users ..

Thank you in advance!
Martin


--
*) and really that *is* R's source code repos.
   All else are mirrors (efficient and convenient ones, I agree)

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: arima/fixed

Martin Maechler
>>>>> Martin Maechler
>>>>>     on Sat, 30 Jan 2021 12:21:14 +0100 writes:

>>>>> Rolf Turner
>>>>>     on Sat, 30 Jan 2021 16:11:32 +1300 writes:

    >> On Fri, 29 Jan 2021 12:47:25 +0000 Nasia Petsa
    >> <[hidden email]> wrote:

    >>> Dear all,
    >>>
    >>> I have the following problem with determining the
    >>> argument fixed in arima function. What is the length of
    >>> argument fixed for an ARIMA(1,0,0)(0,1,1) and what is
    >>> the correct order for the parameters

    >> Hmm.  The help is indeed pretty opaque, isn't it?

    > Can you propose improvements?

    > Here(*) is the source code of the help page

    >   http://svn.r-project.org/R/trunk/src/library/stats/man/arima.Rd

    > We (and future R users) would be glad for less opaque (and
    > still concise) wording, notably in simple enough English
    > for the 90% non-natively English speaking R users ..

    > Thank you in advance!  Martin

In the mean time, Rolf sent me a nicely enhanced arima.Rd
which is now part of R  (R-devel at least):

------------------------------------------------------------------------
r79918 | maechler | 2021-02-01 15:07:32 +0100 (Mon, 01 Feb 2021) | 1 line
Changed paths:
   M src/library/stats/man/arima.Rd
   M tests/Examples/stats-Ex.Rout.save

extended for `fixed` arg, plus ex., thanks to Rolf Turner
------------------------------------------------------------------------

(Unfortunately, I added 1 stray character when slightly editing
 Rolf's version.)

Such _careful_ contributions are welcome, thank you again!

---
Martin

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.