Chinese Science Bulletin

, Volume 51, Issue 23, pp 2926–2930

Theory of multivariate compound extreme value distribution and its application to extreme sea state prediction


DOI: 10.1007/s11434-006-2186-x

Cite this article as:
Liu, D., Wang, L. & Pang, L. CHINESE SCI BULL (2006) 51: 2926. doi:10.1007/s11434-006-2186-x


In this paper, a new type of distribution, multivariate compound extreme value distribution (MCEVD), is introduced by compounding a discrete distribution with a multivariate continuous distribution of extreme sea events. In its engineering application the number over certain threshold level per year is fitting to Poisson distribution and the corresponding extreme sea events are fitting to Nested Logistic distribution, then the Poisson-Nested logistic trivariate compound extreme value distribution (PNLTCED) is proposed to predict extreme wave heights, periods and wind speeds in Yellow Sea. The new model gives more stable and reasonable predicted results.


multivariate compound extreme value distributionNested-logistic modelextreme sea statethreshold value

Copyright information

© Science in China Press 2006

Authors and Affiliations

  1. 1.Disaster Prevention Research InstituteOcean University of ChinaQingdaoChina
  2. 2.Department of MathematicsOcean University of ChinaQingdaoChina
  3. 3.College of EngineeringOcean University of ChinaQingdaoChina