[R] Box.test degrees of freedom

raf.rossignol raphael.rossignol at math.u-psud.fr
Fri Aug 8 11:46:05 CEST 2008


Prof Brian Ripley wrote:
> I think you are referring to its application to the residuals of an 
> ARMA(p, q) fit, and that is not what Box.test says it does.
> It is very easy to edit the code if you want to use a different degrees of
> freedom.
I am also new to R, but it seems to me that there is still something
confusing, not in Box.test but in tsdiag.Arima
Indeed, the help of tsdiag says "The methods for 'arima' and 'StructTS'
[...] use the Ljung-Box version of the portmanteau test." 
So we could expect the degrees of freedom 'h-p-q' to be used, but a look at
tsdiag.Arima shows it uses Box.test at lags h=1:gof.lag, with degrees of
freedom equal to h, and  not h-p-q. Do you think this is a mistake in
tsdiag.Arima or is there some experimental (or theoretical) reason
supporting this choice ?
Best regards

View this message in context: http://www.nabble.com/Box.test-degrees-of-freedom-tp17277964p18888923.html
Sent from the R help mailing list archive at Nabble.com.

More information about the R-help mailing list