Fuzzy Autoregressive Model Using Interval Type Time-Series Data and its Application to the Nikkei Stock Average

By : Yoshiyuki Yabuuchi

Page No: 175-191

Abstract: 
An exact value is not always needed for a time-series analysis, but we must know whether it changes more than a certain amount. In such a case, an interval value with a membership function that has a uniform distribution is appropriate for the time-series analysis. Therefore, this paper proposes a time-series model using interval values. The proposed model classifies time-series data into intervals and uses the center values of the interval to make predictions. When the proposed model is applied to the Nikkei Stock Average, it is confirmed that the proposed model is useful.

Author :
Yoshiyuki Yabuuchi
Shimonoseki City University, Shimonoseki, Yamaguchi 751-8510, Japan.
 

DOI: https://doi.org/10.32381/JCISS.2020.45.1-4.3