arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.02532econ.EMstat.ME
收藏

函数型时间序列的近似因子模型

Approximate Factor Models for Functional Time Series

Institute of Econometrics and Statistics, University of Cologne(科隆大学计量经济学与统计研究所);Department of Economics, Universidad Carlos III de Madrid(马德里卡洛斯三世大学经济系)

Sven Otto, Nazarii Salish

AI总结:

本文提出一种针对函数型时间序列的近似因子模型,利用自协方差结构分解数据,通过累积自协方差算子估计参数,并在死亡率与收益率曲线应用中优于函数型主成分分析。

摘要:

我们提出了一种新颖的近似因子模型,专门用于分析随时间变化的曲线数据。该模型将此类数据分解为两个不同的组成部分:一个低维的可预测因子成分和一个不可预测的误差项。这些成分通过底层函数型时间序列的自协方差结构来识别。模型参数利用累积自协方差算子的特征分量进行一致估计,并提出了一种信息准则以确定合适的因子数量。在死亡率与收益率曲线建模中的应用表明,与广泛使用的函数型主成分分析相比,我们的方法具有关键优势,因为它提供了底层动态的简约结构表示,并在样本外预测性能上有所提升。

英文摘要:

We propose a novel approximate factor model tailored for analyzing time-dependent curve data. Our model decomposes such data into two distinct components: a low-dimensional predictable factor component and an unpredictable error term. These components are identified through the autocovariance structure of the underlying functional time series. The model parameters are consistently estimated using the eigencomponents of a cumulative autocovariance operator and an information criterion is proposed to determine the appropriate number of factors. Applications to mortality and yield curve modeling illustrate key advantages of our approach over the widely used functional principal component analysis, as it offers parsimonious structural representations of the underlying dynamics along with gains in out-of-sample forecast performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑