題 目：Copulas: a tool for modeling the dependence structure of random vectors
時(shí) 間：4月29日上午 10：00—12:00
地 點(diǎn)：主樓418
主講人：Professor Radko Mesiar 斯洛伐克技術(shù)大學(xué)
主講人簡(jiǎn)介：
Radko Mesiar, professor at Slovak University of Technology, Doctor of Science, obtained his PhD. from Comenius University Bratislava in 1979. He is the vice-head of the Department of Mathematics of the Faculty of Civil Engineering, Slovak University of Technology, Bratislava. He has been a visiting professor at several universities in Germany, France, Italy, Austria, Spain, etc. His main fields of interest are the fuzzy sets, fuzzy logic, non-additive measures and integrals, triangular norms, aggregation operators, ergodic theory and entropy. He is an associated editor of international journal Fuzzy Sets and Systems. He is a member of editional board of international journal Cybernetics and international journals Tatra Mount. Math. Publ. and J. Appl. Math
內(nèi)容簡(jiǎn)介：
Copulas are functions that allow a multivariate distribution function to be represented as a function of its one-dimensional marginal distribution functions. Copula means “a link” and is used to describe bivariate cumulative density functions. There are a few applications of copulas in measuring dependence structure in the management literature. For example, Bayesian analysis of accident precursors requires the ability to construct joint prior distributions reflecting such dependencies. Some authors explore the use of copulas to construct the needed prior distributions, and then use these distributions in a Bayesian analysis of hypothetical precursor data. The report will tell us that some properties of copulas and several construction methods, especially when a partial knowledge is available, are included. Some applications are indicated.
