Title :
Copula functions as a tool in statistical modeling and simulation
Author_Institution :
Math. Dept., Univ. of Northen British Columbia, Prince George, BC, Canada
Abstract :
Copulas are functions that join or couple multivariate distribution functions to their one dimensional marginal distribution functions. Alternatively, copulas are multivariate distribution functions whose one-dimensional margins are uniform on the interval (0,1). The appeal of copula function lies in the fact that it eliminates the implied reliance on the multivariate normal or the assumption that dimension are independent. Copula functions provide a convenient way to express joint distributions and simulate correlated variables. Several copulas with varying shapes are available providing flexibility in modelling. We discuss idea of copula functions in statistical modeling and simulation.
Keywords :
data analysis; statistical analysis; statistical distributions; 1D marginal distribution function; copula function; multivariate distribution function; multivariate normal; statistical data analysis; statistical modeling; statistical simulation; Computational modeling; Computer science; Computer simulation; Data analysis; Distribution functions; Gaussian distribution; Mathematics; Random variables; Stochastic processes; Testing; Copulas; Dependence; Multivariate Distribution; Simulation;
Conference_Titel :
Methods and Models in Computer Science, 2009. ICM2CS 2009. Proceeding of International Conference on
Conference_Location :
Delhi
Print_ISBN :
978-1-4244-5051-0
DOI :
10.1109/ICM2CS.2009.5397968