R help - Dec 2011 - Confidence intervals of gls function?

Dear  gls-experts,

while reading and testing some examples of the  book
"introductionary time series analysis with R",
I encountered the following fact which puzzles me.

Confidence intervals for global temperature time series (P99)
computed from general least squares (GLS) to fit the time series.

I repeat the example from the book and get the same results:

temp.gls=gls(temp ~ time(temp),correlation=corAR1(0.7))
print(confint(temp.gls))
                   2.5 %       97.5 %
(Intercept) -39.80571914 -28.49658509
time(temp)    0.01442274   0.02011148

But to my surprise the value of the lag 1 acf does not matter:

temp.gls=gls(temp ~ time(temp),correlation=corAR1(0.1))
print(confint(temp.gls))
                   2.5 %       97.5 %
(Intercept) -39.80571914 -28.49658509
time(temp)    0.01442274   0.02011148

I could set it even to 0.0 or -0.1 and get the same  result.

Why the confidence interval should be independent of the value of the
autocorrelation?

Many thanks for any hints in this matter, best regards, Adolf stips



------------------------------------------------
Adolf Stips (adolf.stips@jrc.ec.europa.eu)
Global Environment Monitoring unit
CEC Joint Research Centre, TP 272
I-21027 Ispra, Italy
Tel: +39-0332-789876
Fax: +39-0332-789034
I know that I do not know, but even that not for sure!
------------------------------------------------
"The views expressed are purely those of the writer and may not in any
circumstances be regarded as stating an official position of the European
Commission."
 


	[[alternative HTML version deleted]]