Two extreme value processes arising in hydrology
Keyword(s):
Let Tn be the time of occurrence of the nth flood peak in a hydrological system and Xn the amount by which the peak exceeds a base level. We assume that ((Tn, Xn)) is a Poisson random measure with mean measure μ(dx) K(x, dy). In this note we characterize two extreme value processes which are functionals of ((Tn, Xn)). The set-parameterized process {MA} defined by MA = sup {Xn:Tn ∈ A} is additive and we compute its one-dimensional distributions explicitly. The process (Mt), where Mt = sup{Xn: Tn ≦ t}, is a non-homogeneous strong Markov process. Our results extend but computationally simplify those of previous models.
1976 ◽
Vol 13
(01)
◽
pp. 190-194
◽
Keyword(s):
2011 ◽
Vol 14
(03)
◽
pp. 335-351
◽
1972 ◽
Vol 23
(2)
◽
pp. 114-120
◽
1995 ◽
Vol 47
(1)
◽
pp. 165-200
◽
Keyword(s):
2015 ◽
Vol 742
◽
pp. 419-428