[R-sig-ME] correlation structure with AR(1)
FMH
kagba2006 at yahoo.com
Thu Sep 3 18:39:14 CEST 2009
Dear All,
Could someone please advice me the difference between lme function with correlation structure of the residual from AR(1) process and without this correlation structure. I found from the help menu shown below that if we do not declare any value in corAR1, by default, the function will assume there is no autocorrelation i.e. 0.
Does this meant we can just simply ignore the correlation structure in the model and just use a simple command in lme without including corAR1? Please correct me if i'm wrong.
###################################################################################
Usage
corAR1(value, form, fixed)
Arguments
value the value of the lag 1 autocorrelation, which must be between -1 and 1. Defaults to 0 (no autocorrelation).
###################################################################################
Let see on few examples from the help menu. I noticed that these two examples yield different results in term of the fixed and random effects parameters. From what i understand, we should get the same results as the second object, fm2Ovar.lme does not have any autocorrelation in its AR(1) correlation structure as the default value is used.
Could someone please advice on the reason of these differences?
###################################################################################
# Pinheiro and Bates, p. 240
fm1Ovar.lme <- lme(follicles ~ sin(2*pi*Time) + cos(2*pi*Time), data = Ovary, random = pdDiag(~sin(2*pi*Time)))
fm2Ovar.lme <- update(fm1Ovar.lme, correlation = corAR1())
###################################################################################
Thank you
Fir
More information about the R-sig-mixed-models
mailing list