Hi:
I am using the following code to read a data set in txt in R and using the
follwoing model. But it seems to give me an error ' expected variable name
error pos 134022'. Any help is greatly appreciated.
Code:
anal.data <- read.table("nausea.txt", header=T, sep="\t")
list(names(anal.data))
attach(anal.data)
n.samples <- dim(anal.data) [1] # number of data points
n.params <- dim(anal.data)[2] - 2 # number of parameters to estimate
n.sites <- length(unique(SITEID))
data.bugs <- list("NAUSEA"=NAUSEA,"SITEID"=SITEID,"BMI"=BMI,
"USUBJID"=USUBJID,"n.samples"=n.samples,"n.sites"=n.sites,"n.params"=n.params)
bugsData(data.bugs, fileName = "nauseadata.txt")
inits.bugs <- list("b"=rep(0,n.params),"alpha"=rep(0,n.sites), "tau"=1)
bugsInits(list(inits.bugs), fileName = "nauseainit.txt")
> modelCheck("nausea_random.txt") # check model file
model is syntactically correct
> modelData("nauseadata.txt") # read data file
expected variable name error pos 134022
Model statement:
model
{
for (i in 1:n.samples)
{NAUSEA[i] ~ dbin(p[i],1)
logit(p[i]) <- alpha[SITEID[i]] + b[1] + b[2]*BMI[i]}
for(k in 1:n.params)
{b[k]~ dnorm(0.0,tau)}
for (j in 1:n.sites)
{alpha[j]~dnorm(0.0,1.0E-10)}
tau ~ dgamma(0.001,0.001)
}
Sample Dataset:
USUBJID SITEID BMI NAUSEA
01 0
01 0
01 0
01 0
01 0
01 0
01 0
01 0
01 0
3020101648 01 25.62 0
3020101649 01 30.54 0
3020101650 01 26.68 1
3020101651 01 26.56 0
3020101652 01 22.96 0
3020101653 01 26.27 0
3020101666 01 26.15 1
3020101667 01 30.18 0
3020101668 01 24.33 0
3020101669 01 44.72 1
3020101670 01 33.54 1
3020101671 01 36.39 1
3080101561 01 30.13 1
3080101562 01 25.8 1
3080101564 01 31.07 1
3080101565 01 26.53 0
3080101566 01 29.3 0
30801 01694 01 28.4 1
3080101695 01 26.03 1
3080101696 01 27.43 1
3080101697 01 31.96 0
3080101698 01 28.76 0
3080101699 01 28.4 1
3080101700 01 29.33 0
3080101701 01 36.02 0
3080101768 01 31.05 1
Thanks
Anamika
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
