I need some advice on Rick Wicklin's implementation of the Value-Maurelli method in SAS/IML from his book (section 16.11), "Simulating data with SAS" (highly recommended book by the way). The method allows one to generate Monte Carlo simulation data with pre-specified marginal skewness, kurtosis and joint linear correlation (as gauged by Pearson's r). Great stuff, but I find that I get this error (see below a simple bivariate example) when I try to specify significant skewness, with low kurtosis. It looks like a type of input format error, but I've used it a lot and it seems rather a problem with specifying high skew with low kurtosis (if I bump up the kurtosis in this example, eventually the problem goes away). It would be nice if I could find out if this is a limitation of the method itself or my own error? Thank you for taking the time to consider my question. 250 proc iml; NOTE: IML Ready 251 load module=_all_; NOTE: Opening storage library WORK.IMLSTOR 252 skew = {2 2}; 253 kurt = {0 0}; 254 R = {1.0 0.5, 255 0.5 1.0}; 256 V = VMTargetCorr(R, skew, kurt); ERROR: (execution) Invalid argument or operand; contains missing values.
... View more