Identify time-invariant observations in a pdata.frame in plm

Question

Suppose I have a pdata.frame (using the plm package in r) like so:

> df <- data.frame(id=c(1,1,1,2,2,2,3,3,3,4,4,4), time=rep(1:3,4),obs=c(1,2,3,1,1,1,1,1,2,0,0,0))
> pdf <- pdata.frame(df)
> pdf
    id time obs
1-1  1    1   1
1-2  1    2   2
1-3  1    3   3
2-1  2    1   1
2-2  2    2   1
2-3  2    3   1
3-1  3    1   1
3-2  3    2   1
3-3  3    3   2
4-1  4    1   0
4-2  4    2   0
4-3  4    3   0

I have an observation which does not vary with time in some of the id indices, but does in others. I would like to find the ones that do not vary with time, i.e. I want to extract something that looks like

    id time obs
2-1  2    1   1
2-2  2    2   1
2-3  2    3   1
4-1  4    1   0
4-2  4    2   0
4-3  4    3   0

is there an easy way to do this?

Answer 1

Something like this?

pdf[!ave(pdf$obs, pdf$id, FUN = function(x) length(unique(x)) != 1), ]
 # id time obs
 # 2-1  2    1   1
 # 2-2  2    2   1
 # 2-3  2    3   1
 # 4-1  4    1   0
 # 4-2  4    2   0
 # 4-3  4    3   0