hello, I'm searchinf for some syntax for 95% confidence interval of kappa (ICC) for inter-observer agreement. I followed as described in R documentation, For IC 95%, it works well for bootstrap as follow : > icc.boot <- function(data,x) {icc(data[x,])[[7]]} > bootpbf <- boot(lsm[,c(21,22)],icc.boot,1000) > quantile(bootpbf$t,c(0.025,0.975) but for simple ICC, I got only ICC but not for its CI 95% > pbf<-icc(lsm[,c(21,22)]) > quantile(pbf$t,c(0.025,0.975)) 2.5% 97.5% NA NA Warning message: is.na() applied to non-(list or vector) in: is.na(x) How can I manage it to solve the problem of NA and get CI 95% of that kappa? thank you for all your advices. Tin Tin [[alternative HTML version deleted]]