Title: Modeling interval financial time series
Authors: Liang-Ching Lin - National Cheng Kung University (Taiwan) [presenting]
Li-Hsien Sun - National Central University (Taiwan)
Abstract: In financial economics, a large number of analysis and models are developed based on the daily closing price, or even at lower frequencies such as weekly or monthly. However, some valuable intra-daily information such as maximum and minimum prices may be discarded. We propose an interval time series model, including the maximum, minimum and closing prices, and then apply the proposed model to forecast the interval. The likelihood function and the corresponding maximum likelihood estimates (MLEs) are obtained by using the stochastic differential equation and the Girsanov theorem. The efficiency of the proposed estimators is illustrated by the simulation study. Finally, in the real data analysis for S\&P 500 index, we show that the forecast of proposed method outperforms than several alternatives.