Hi Miguel,
You don't seem to have defined "J" before line 2. Maybe that is
the problem.
Jim
On Mon, May 1, 2017 at 2:57 PM, Miguel Angel Hombrados Herrera
<mangelhombradosherre at unm.edu> wrote:> Hello
>
>
> Ive been working on a stan program in Rstudio. Im kind of new on this, so
probably my question is trivial, However I was not able to find information
about this.
>
> The error Im getting when I run my stan code is:
>
>
> PARSER EXPECTED: whitespace to end of file.
> FOUND AT line 2:
>
>
> The code is:
>
> iter=500
> alphamcmc=matrix(0,ncol=J,nrow=iter)
> betamcmc=NULL
> mu_alpha=NULL
> sigma_alpha_2=NULL
> sigma_y_2=NULL
> #set initial values
> alphamcmc[1,]=rep(mean(y),J)
> betamcmc[1]=70
> mu_alpha[1]=mean(y)
> sigma_alpha_2[1]=300
> sigma_y_2[1]=350
> #mcmc iteration
> for(m in 2:iter){
> #update alpha vector
> for(j in 1:J){
> sj=sum(source==j)
> var=1/(sj/sigma_y_2[m-1]+1/sigma_alpha_2[m-1])
> temp=0
> for(i in 1:N){temp=temp+1*(source[i]==j)*(y[i]-betamcmc[m-1]*x[i])}
> #sum up (y_i-beta x_i ) for those belonging to group j
> mean=var*(temp/sigma_y_2[m-1]+mu_alpha[m-1]/sigma_alpha_2[m-1])
> alphamcmc[m,j]=rnorm(1,mean,sqrt(var))
> }
> #update beta
> var=sigma_alpha_2[m-1]/(sum(x^2))
> mean=sum(x%*%(y-alphamcmc[m,source])/sum(sum(x^2)))
> betamcmc[m]=rnorm(1,mean,sqrt(var))
> #update mu_alpha
> #update sigma_alpha_2
> sigma_alpha_2[m]=rinvgamma(1,shape=J/2,rate=sum((alphamcmc[m,]
> -mu_alpha[m])^2/2))
> #update sigma_y_2
> sigma_y_2[m]=rinvgamma(1,shape=N/2,rate=sum((y-alphamcmc[m,source]-
> betamcmc[m]*x)^2/2))
> }
> nburn=200
> apply(alphamcmc[(nburn+1):iter,],2,mean)
> apply(betamcmc[(nburn+1):iter],2,mean)
>
> Ive been searching for wrong spaces or tabulations, but I was not able to
find anything.
>
> I really would appreciate your help.
> Thaknk you.
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.