st: Intraclass correlation coefficient analyses in STATA

[Ringdal Kjetil Gorseth <kjetil.ringdal@norskluftambulanse.no>]

Hi

I am trying to calculate  Intraclass Correlation Coefficients (ICC) in STATA, but have run into some problems.

I wonder if you could give some info abut how to calculate ICC in STATA for a two-way mixed model (ICC[3,1]) measuring absolute agreement between two raters (Each target is rated by each of the same k raters, who are the only raters of interest). I would like to analyse agreement between a group a 10 raters raters, but focus on analysing two raters at a time.

See the paper "Shrout P, et al. Intraclass Correlations: Uses in Assessing Rater Reliability. Psychol Bull. 1979; 86(2):420" on different types of ICC.

In SPSS there is an easy way of doing this (I can find the two-way mixed, two-way random, and one-way random effects models), but I cannot find the same in STATA. I have tried the –loneway– command, but this does not produce the same ICC or the same 95% CI values as in SPSS. In SPSS, I can also analyse all raters against each other.

Neither the –icc23– or the –icccof– commands produce the same values as the SPSS command.

Do you have any other suggestions on how to do the analyses in STATA?

Kind regards
Dr. Kjetil Ringdal

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/