Hello please note that the code at
https://stat.ethz.ch/pipermail/r-help/2006-August/110892.html to compute indices of skewness and kurtosis for the skew-t distribution is not correct. It has been kindly pointed out that i made some error in this code, which was a bit too quickly copied from the paper. The 'sn' package already contains a facility for computing the cumulants, namely the function st.cumulants which computes cumulants up to order 4. With this function, it is immediate to compute skewness and kurtosis. Examples: > cum<- st.cumulants(0,2,3,5) > v <- cum[2] > skew<- cum[3]/v^1.5 > kurt<- cum[4]/v^2 > print(c(v, skew,kurt)) [1] 3.424 2.127 16.256 I thank Adelchi Azzalini for pointing me out the error, my apologies to the R list users and thanks to him. luc ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.