Estimation of Variograms by Monotone, Conditionally Negative Definite Functions with Applications in Forestry

基于完全单调函数的协方差模型和变异函数受到越来越多的关注，因为理论和实践上的原因：(I)单变量模型构成重要的参数类；(Ii)在单变量、平稳和各向同性随机场的情况下可用于非参数估计的方法；(Iii)非平稳模型、时空模型和多变量模型的积木。本项目的目标是加深对这类模型的现有知识，并开发适用于更复杂情况的推理方法。

Covariance models and variograms that are base on completely monotone functions gain increasing consideration, for both theoretical and practical reasons: (i) univariate models comprise important parametric classes; (ii) available methods for the non-parametric estimation in the case of univariate, stationary and isotropic random fields; (iii) building block for non-stationary models, space-time models and multivariate models.The goal of the project is to deepen the current knowledge of the class and to develop inference methods for more complex situations.