Trawl processes are continuous-time, stationary and infinitely divisible processes which can describe a wide range of possible serial correlation patterns in data. In this paper, we introduce new simulation algorithms for trawl processes with monotonic trawl functions and establish their error bounds and convergence properties. We extensively analyse the computational complexity and practical implementation of these algorithms and discuss which one to use depending on the type of L\'evy basis. We extend the above methodology to the simulation of kernel-weighted, volatility modulated trawl processes and develop a new simulation algorithm for ambit fields. Finally, we discuss how simulation schemes previously described in the literature can be combined with our methods for decreased computational cost.
翻译:拖网过程是连续的、固定的和无限分散的过程,可以描述数据中可能的一系列系列关联模式。在本文中,我们为具有单声拖网功能的拖网过程采用新的模拟算法,并确立其误差界限和趋同特性。我们广泛分析这些算法的计算复杂性和实际应用,并根据L\'evy基础的类型讨论应使用哪种算法。我们将上述方法推广到内核加权、易变性调控拖网过程的模拟,并为范围领域开发新的模拟算法。最后,我们讨论了如何将文献中先前描述的模拟方法与我们降低计算成本的方法结合起来。