An approach to modeling asymmetric multivariate spatial covariance structures
An approach to modeling asymmetric multivariate spatial covariance structures
复制标题
DOI：
10.1016/j.jmva.2011.05.010
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Bo Li;Hao Zhang
中科院分区：
文献类型：
--
作者：
Bo Li;Hao Zhang
我们提出了一个框架，在光的延迟效应来建模的多元协方差函数，往往表现在真实的数据的不对称性。这种方法可以赋予任何有效的对称多元协方差函数建模非对称性的能力，并且非常容易实现。我们的模拟和真实的数据的例子表明，非对称的多元协方差函数的基础上，我们的方法可以实现显着的改善，预测对称模型。
We propose a framework in light of the delay effect to model the asymmetry of multivariate covariance functions that is often exhibited in real data. This general approach can endow any valid symmetric multivariate covariance function with the ability of modeling asymmetry and is very easy to implement. Our simulations and real data examples show that asymmetric multivariate covariance functions based on our approach can achieve remarkable improvements in prediction over symmetric models.