Name
Title | ||
|---|---|---|
Generating Multivariate Mixture of Normal Distributions using a Modified Cholesky Decomposition |
Abstract | ||
|---|---|---|
Mixture of normals is a more general and flexible distribution for modeling of daily changes in market variables with fat tails and skewness. An efficient analytical Monte Carlo method was proposed by Wang and Taaffe for generating daily changes using a multivariate mixture of normal distributions with arbitrary covariance matrix. However the usual Cholesky decomposition will fail if the covariance matrix is not positive definite. In practice, the covariance matrix is unknown and has to be estimated. The estimated covariance may be not positive definite. We propose a modified Cholesky decomposition for semi-definite matrices and also suggest an optimal semi-definite approximation for indefinite matrices |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/WSC.2006.323100 | Winter Simulation Conference |
Keywords | Field | DocType |
normal distribution,optimal semi-definite approximation,usual cholesky decomposition,generating multivariate mixture,cholesky decomposition,modified cholesky decomposition,covariance matrices,semi-definite matrix,daily change,arbitrary covariance matrix,monte carlo methods,normal distributions,indefinite matrix,analytical monte carlo method,multivariate mixture,covariance matrix,estimated covariance,fat tail,positive definite,monte carlo method | Applied mathematics,Covariance function,Estimation of covariance matrices,Simulation,Incomplete Cholesky factorization,Minimum degree algorithm,Multivariate normal distribution,Statistics,Wishart distribution,Mathematics,Covariance,Cholesky decomposition | Conference |
ISBN | Citations | PageRank |
1-4244-0501-7 | 2 | 0.46 |
References | Authors | |
5 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jin Wang | 1 | 8 | 3.50 |
| Chunlei Liu | 2 | 351 | 171.80 |