Title: Symbolic interval-valued data analysis for time series based on auto-interval-regressive models
Authors: Liang-Ching Lin - National Cheng Kung University (Taiwan) [presenting]
Abstract: Interval-valued time series data are considered. To characterize interval time series data, we propose an auto-interval-regressive (AIR) model using the order statistics from normal distributions. Furthermore, to better capture heteroscedasticity in volatility, we designate an autoregressive conditional heteroscedasticity (AIR-ARCH) model. The likelihood functions of AIR and AIR-ARCH models are derived to obtain the maximum likelihood estimator. The corresponding predicted formulae are also given. Monte Carlo simulations are conducted to evaluate our methods of estimation, confirming their validity. Real data example is also carried out for the S\&P 500 Index for illustration.