Trend locally stationary wavelet processes
Trend locally stationary wavelet processes
复制标题
DOI：
10.1111/jtsa.12643
复制
发表时间：
2022-11
影响因子：
0.9
通讯作者：
Euan T. McGonigle;Rebecca Killick;M. Nunes
中科院分区：
文献类型：
--
作者：
Euan T. McGonigle;Rebecca Killick;M. Nunes
在实践中观察到的大多数时间序列在本文中表现出一阶和二阶非平稳性。局部固定的小波过程，并扩展了局部固定小波模型的适用性，以包括趋势组件。串联数量并表明我们的估计器通过对系列趋势做出适当的假设来互相隔离，我们通过分析全球平均海温时间序列来证明该方法的实用性，从而突出了不断变化的气候的影响。
Most time series observed in practice exhibit first‐ as well as second‐order non‐stationarity. In this article we propose a novel framework for modelling series with simultaneous time‐varying first‐ and second‐order structure, removing the restrictive zero‐mean assumption of locally stationary wavelet processes and extending the applicability of the locally stationary wavelet model to include trend components. We develop an associated estimation theory for both first‐ and second‐order time series quantities and show that our estimators achieve good properties in isolation of each other by making appropriate assumptions on the series trend. We demonstrate the utility of the method by analysing the global mean sea temperature time series, highlighting the impact of the changing climate.