Hello,
I would like to fit correlation structures with nlme, but R crashes.
My data is similar to the "growth of orange trees" example from
Pinheiro and
Bates (2000),
but data are not equally spaced in time, as the last observation is taken
after 6 days ( and not 2 as the others).
This is the code I'm using:
library(nlme)
DO<-c(0.107,0.118,0.271,0.431,0.597,0.909,1.259,1.688,2.301,
0.107,0.150,0.200,0.325,0.425,0.641,0.860,1.329,1.780,
0.101,0.159,0.204,0.484,0.663,1.019,1.335,1.880,1.927)
mtime<-rep(c(seq(1,15,2),21),3)
Subject<-rep(1:3,each=9)
dataset<-data.frame(DO=DO, mtime=mtime, Subject=Subject)
Joy <- groupedData( DO ~ mtime | Subject, data = dataset)
m0<-nlsList( DO ~ SSlogis(mtime, asym, xmid, scal), data = Joy)
m1.nlme<-nlme(m0)
m3.nlme<-update(m1.nlme,random=(asym~1), weights = varPower() )
m4.nlme <- update( m3.nlme, corr = corExp(form = ~ mtime) ) # R crashes
m5.nlme <- update( m3.nlme, corr = corRatio(form = ~ mtime) ) # R crashes
m6.nlme <- update( m3.nlme, corr = corSpher(form = ~ mtime) ) # R crashes
m7.nlme <- update( m3.nlme, corr = corLin(form = ~ mtime) ) # R crashes
m8.nlme <- update( m3.nlme, corr = corGaus(form = ~ mtime) ) # R crashes
*sessionInfo():*
R version 2.13.0 (2011-04-13)
Platform: i386-pc-mingw32/i386 (32-bit)
locale:
[1] LC_COLLATE=French_France.1252 LC_CTYPE=French_France.1252
LC_MONETARY=French_France.1252 LC_NUMERIC=C
LC_TIME=French_France.1252
attached base packages:
[1] grDevices datasets splines graphics stats tcltk utils
methods base
other attached packages:
[1] nlme_3.1-100 svSocket_0.9-51 TinnR_1.0.3 R2HTML_2.2
Hmisc_3.8-3 survival_2.36-5
loaded via a namespace (and not attached):
[1] cluster_1.14.0 drc_2.1-4 grid_2.13.0 lattice_0.19-23
svMisc_0.9-61 tools_2.13.0
Thank you for your help,
Andreea Borla
[[alternative HTML version deleted]]
