[R] Dummy variable in ARIMA

[peter dalgaard]

> On 26 Feb 2015, at 17:29 , Mikael Olai Milhøj <mikaelmilhoj at gmail.com> wrote:
> 
> Hi.
> 
> First of all, thx. But when using in arima(...xreg=fact,...) then fact
> should be a vector and not a factor variable? Maybe I should have been more
> clear in my first mail, sorry. Or else I have to dig deeper into factors.
> 

You can always do things like as.numeric((1:50) %in% (4:6)), but longer term I think it is more generalizable to play with model.matrix(), i.e. M <- model.matrix(~fact). As far as I recall, arima() will automatically include a constant so you need to say xreg=M[,-1] to get rid of the column of ones.


> 
> /Mikael
> 
> On Thu, Feb 26, 2015 at 5:17 PM, Bert Gunter <gunter.berton at gene.com> wrote:
> 
>> Inline.
>> 
>> Cheers,
>> Bert
>> 
>> Bert Gunter
>> Genentech Nonclinical Biostatistics
>> (650) 467-7374
>> 
>> "Data is not information. Information is not knowledge. And knowledge
>> is certainly not wisdom."
>> Clifford Stoll
>> 
>> 
>> 
>> 
>> On Thu, Feb 26, 2015 at 8:02 AM, Mikael Olai Milhøj
>> <mikaelmilhoj at gmail.com> wrote:
>>> Hi all
>>> 
>>> I have been searching on the web in vain. I want to include a dummy
>>> variable in my ARIMA model. Let's say that I want to make an AR(1) model
>>> for X including a dummy variable which should be 1 for observation 4,5,6
>>> and zero otherwise (let's say that there is 50 observations in total).
>> How
>>> do I make that?
>> 
>> You don't, really.
>> 
>> 1. Go through an R tutorial so that you understand the concept of
>> factors and how they are used in R modeling.
>> 
>> 2. fact <- factor( (1:50) %in% (4:6))
>> 
>> Cheers,
>> Bert
>> 
>>> 
>>> This does the trick but seems inefficient: dummy<-c(rep(0,3), rep(1,3),
>>> rep(0,44))
>>> 
>>> Thx in advance
>>> 
>>> Best regards
>>> /Mikael
>>> 
>>>        [[alternative HTML version deleted]]
>>> 
>>> ______________________________________________
>>> R-help at r-project.org 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.
>> 
> 
> 	[[alternative HTML version deleted]]
> 
> ______________________________________________
> R-help at r-project.org 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.

-- 
Peter Dalgaard, Professor,
Center for Statistics, Copenhagen Business School
Solbjerg Plads 3, 2000 Frederiksberg, Denmark
Phone: (+45)38153501
Email: pd.mes at cbs.dk  Priv: PDalgd at gmail.com