Click here to go to the previous page
An Introduction to Copulas and Their Applications Webinar
Program Code:
170
PRESENTER
:
Curtis Gary Dean is a Fellow of the Casualty Actuarial Society and member of the American Academy of Actuaries. He is currently the Lincoln Financial Group Distinguished Professor of Actuarial Science at Ball State University. Prior to joining Ball State he worked as an actuary at American States Insurance and SAFECO. He left Ball State in 2006 to work in commercial lines predictive modeling at Travelers, but later returned to Ball State. His current actuarial interests include predictive modeling and credibility theory.
Gary has been an active contributor to the CAS. A few of the more noteworthy contributions include Chair of the Examination Committee, first Editor-in-Chief for Variance, a member of the Board of Directors, VP Administration and member of the Executive Council, Chair of the University Relation Committee, and Chair of the Investment Committee. He was a recipient of the "Above & Beyond Achievement Award" in 2009.
|
Description
Program Description
"An Introduction to Copulas" will be an introductory session targeted to the general actuarial population. The presentation will cover the basic mathematical theory of copulas, explain why copulas are useful, and provide examples of their use. Intuition and understanding will be given priority over mathematical complexity.
Copulas are useful for modeling dependencies in a variety of situations. For example, a claim loss payment and its associated ALAE will show a dependency relationship. Higher claim payments more likely produce higher ALAE amounts. Prices of financial assets can be linked via copula models. Joint survival models where lives are dependent can be constructed with copulas.
Intended Audience
The general actuarial population who want to learn the basic mathematics of copulas and applications of copulas in actuarial science. The audience should have a basic understanding of probability theory including the concepts of random variables, independence, and joint distributions.