ICC with sparse data

[Stuart Luppescu <s-luppescu@uchicago.edu>]

Hello, I need to calculate an intra-class correlation or inter-rater
reliability on a sparse data matrix. That is, I have about seven hundred
subjects that are being rated by about 40 or 50 raters, but each subject
is rated by only 1 or 2 raters. Some raters rate about 24 subjects;
others only 2 or 3. Since all the standard methods such as icc() use
listwise deletion, I'm going to lose all my data. Is there a way around
this problem?
-- 
Stuart Luppescu -=-=- slu <AT> ccsr <DOT> uchicago <DOT> edu
CCSR at U of C ,.;-*^*-;.,  ccsr.uchicago.edu
     (^_^)/    才文と智奈美の父
[Crash programs] fail because they are based on the theory that, 
with nine women pregnant, you can get a baby a month.
                -- Wernher von Braun