论文信息 - Multivariate Stochastic Dominance and Moments

Multivariate Stochastic Dominance and Moments

The sequence ≥nd of nth degree stochastic dominances for d-dimensional distribution functions is defined. It is shown that, under some regularity conditions, ≥nd implies ≥nd−1 for the (d − 1)-dimensional marginals. Also some necessary conditions for ≥nd are established. These conditions, which involve moments, are analogous to the ones proved by Fishburn (1980b) and O'Brien (1984) for univariate distributions.

Marco Scarsini | George L. O'Brien

[1] G. Simons,et al. Inequalities for Ek(X, Y) when the marginals are fixed , 1976 .

[2] Peter C. Fishburn,et al. Continua of stochastic dominance relations for bounded probability distributions , 1976 .

[3] Marco Scarsini,et al. On measures of concordance , 1984 .

[4] Ward Whitt,et al. Comparison methods for queues and other stochastic models , 1986 .

[5] Larry G. Epstein,et al. Increasing Generalized Correlation: A Definition and Some Economic Consequences , 1980 .

[6] A. Tchen. Inequalities for distributions with given marginals , 1976 .

[7] G. L. O'Brien. Stochastic Dominance and Moment Inequalities , 1984, Math. Oper. Res..

[8] Marco Scarsini,et al. Stochastic dominance with pair-wise risk aversion , 1985 .

[9] Tomasz Rolski,et al. Order relations in the set of probability distribution functions and their applications in queueing theory , 1976 .

[10] Peter C. Fishburn,et al. Stochastic Dominance and Moments of Distributions , 1980, Math. Oper. Res..

[11] Marco Scarsini,et al. Dominance Conditions for Multivariate Utility Functions , 1988 .