Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/45803 
Year of Publication: 
1998
Series/Report no.: 
Discussion Papers in Statistics and Econometrics No. 1/98
Publisher: 
University of Cologne, Seminar of Economic and Social Statistics, Cologne
Abstract: 
We consider four orthant stochastic orderings between random vectors X and Y that have finitely discrete probability distributions in IRk. For each of the orderings conditions have been developed that are necessary and sufficient for dominance of Y over X. We present an algorithm that checks these conditions in an efficient way by operating on a semilattice generated by the support of the two distributions. In particular, the algorithm can be used to compute multivariate Smirnov statistics.
Subjects: 
Multivariate stochastic orders
decision under risk
comparison of empirical distribution functions
Document Type: 
Working Paper

Files in This Item:
File
Size
318.34 kB
271.22 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.