re: Re: st: intracluster correlation coefficient (ICC)

[David Airey <david.airey@vanderbilt.edu>]

Joseph Coveney said:

> -findit intraclass- brings up -loneway-, if that's what you're looking 
> for.
>
> A few years ago, I adapted Robert M. Hamer's SAS macro that provided 
> for all of
> the intraclass correlation coefficients (and their confidence 
> intervals)
> described in P. E. Shrout and J. L. Fleiss, Intraclass correlations: 
> Uses in
> assessing rater reliability. _Psychological Bulletin_ 86:420-428, 
> 1979.  It
> worked for balanced datasets (it called -anova-) for all of the 
> various ICCs,
> and for unbalanced datasets (it called -xtreg-) one type of ICC.  
> StataCorp's
> rewrite of -anova- a while back broke it for some reason that I wasn't 
> able to
> uncover.  Datasets in practice are rarely nicely balanced, so there 
> hasn't been
> much incentive to fix it.
>
> When -xtmixed- is available, I plan go back and re-work it, and add the
> additional ICCs described in K. O. McGraw and S. P. Wong, Forming 
> inferences
> about some intraclass correlation coefficients. _Psychological 
> Methods_ 1:30-
> 46, 1996.
That would be great! It might make a good SJ article or note. I 
remember one thread on ICC in this list:

http://www.stata.com/statalist/archive/2003-10/msg00804.html

-Dave

*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/