[R] How to specify an ARMA(1, [1,4]) model?

[Rolf Turner]

Not clear to me what the OP really wants.  Perhaps the seasonal
model is what's required; perhaps an arima(1,0,4) model with
theta_2 and theta_3 constrained to be 0.  The latter can be
achieved with

	arima(x,order=c(1,0,4),fixed=c(NA,NA,0,0,NA,NA))

Or perhaps it's something else entirely that's wanted ....

	cheers,

		Rolf Turner


On 14/10/2009, at 7:47 AM, Duncan Murdoch wrote:

> On 10/13/2009 2:35 PM, Len Vir wrote:
>> Hi,
>>
>> I'm trying to model an ARMA(1,[1,4]),
>> i.e. I want only lags 1 and 4 of the Moving Average part.
>> It's the '[1,4]' part that is giving me a problem.
>>
>> I've tried different arma's and arima's in different packages,  
>> namely:
>> packages tseries, fArma, FinTS, timeSeries, TSA, Zelig, ds1, forecast
>>
>>
>> For example, with package FinTS:
>>
>>> ( ARIMA(y, order=c(1,0,c(1,4)))  )
>> Error in arima(x = x, order = order, seasonal = seasonal, xreg =  
>> xreg,  :
>>   'order' must be a non-negative numeric vector of length 3
>>
>> Using ARIMA(1,0,1) with a seasonal argument for lag 4
>> does not get me any further.
>
> What's wrong with
>
> arima(x, order=c(1,0,1), seasonal=list(order=c(0,0,1), period=4))
>
> using stats::arima?
>
> Duncan Murdoch
>
>>
>>
>> With package Zelig I got:
>>
>>> (  zelig(Diff(lppi,1) ~ one + lag.y(1) + lag.eps(1) + lag.eps(4) ,
>> model="arima"  , data=Q)  )
>> Error in model.frame.default(mf$formula, data) :
>>   invalid type (list) for variable 'lag.eps(1)'
>>
>> I get basically the same kind of answers with other packages
>> and with different configurations.



######################################################################
Attention:\ This e-mail message is privileged and confid...{{dropped:9}}