Solved – Longitudinal models in R and WINBUGS or JAGS

jagspanel datar

I've tried to use R to fit some longitudinal models, mostly via lmer and nlme packages. However, it seems that many standard models are lacking, such as antedependence models or factor analytic models for covariance matrices. These models are readily available in SAS.

Would anyone recommend other packages for the job in R? I don't really care if I use to work in a frequentist or bayesian world as long as I have more modeling flexibility. I would also be interested in doing that in WINBUGS/JAGS.

Best Answer

Longitudinal and mixed models in BUGS is talked about in Ch. 10 of Bayesian Ideas and Data Analysis. Below is a link to the book website which has some example code.

http://www.ics.uci.edu/~wjohnson/BIDA/BIDABook.html

Related Solutions

Solved – How to combine step(x) and dbern(p) in JAGS/WinBUGS

In JAGS, you can't reuse, in your case, y[j] as you sometimes can in WinBUGS. Instead, you create "new" data out of the data that you pass to JAGS in a data block at the top of the code (i.e., before the model step):

data {
  for (j in 1:N) {
    y[j] <- step(t.2[j] - t.1[j]) 
  }
}

You can then use y[j] on the left hand side of distributions in the model step:

model {
  for (j in 1:N) {
    ...
    y[j] ~ dbern(py)
    ...
  }
}

This can't be done in WinBUGS, however, as there's no data block; instead, you should just pass a precalculated variable y to WinBUGS.

Solved – JAGS: unobserved parents and intialization

The next step with this particular error message should (always ?) be to check the specific node mentioned in the error message and its parents. This sounds like a lot of work when you have large matrices of initial values but the point is that you are likely making a small number of mistakes in generating those values. Each time you trace the error message to a particular problematic node you will be able to eliminate at least one mistake and fix a lot of bad initial values.

In this case your model is simple enough that having alpha/beta initialized to all zeros should take care of most problems. If alpha/beta are zero then the derived values for phi/p would be consistent with all non-negative X's which means the only inconsistency left is that sum(X[i,]) != n[i]...

Best Answer

Related Solutions

Solved – How to combine step(x) and dbern(p) in JAGS/WinBUGS

Solved – JAGS: unobserved parents and intialization

Related Question