EcoSta 2022: Start Registration
View Submission - EcoSta2022
A0687
Title: Component decomposition of the Nikkei stock average time series using moving linear modeling approach Authors:  Koki Kyo - Niigata University of Management (Japan) [presenting]
Abstract: A moving linear modeling (MLM) approach is developed to decompose a time series into trend and fluctuation components. The features of the proposed approach are as follows: It is only necessary to set a local linear model for the trend component and is not necessary to introduce any model for the fluctuation component in which the trend and fluctuation components are uncorrelated. We can decompose a time series into several components by using the MLM approach so we can analyze each component using a simple model. As an illustration, we apply the MLM approach to analyze the daily time series of the Nikkei stock average in Japan.