Abstract
In this study, a network autoregressive model with GARCH effects, denoted by NAR-GARCH, is proposed to depict the return dynamics of stock market indices. A GARCH filter is employed to marginally remove the GARCH effects of each index, and the NAR model with the Granger causality test and Pearson’s correlation test with sharp price movements is used to capture the joint effects caused by other indices with the most updated market information. The NAR-GARCH model is designed to depict the joint effects of nonsynchronous multiple time series in an easy-to-implement and effective way. The returns of 20 global stock indices from 2006 to 2020 are employed for our empirical investigation. The numerical results reveal that the NAR-GARCH model has satisfactory performance in both fitting and prediction for the 20 stock indices, especially when a market index has strong upward or downward movements.
Highlights
The prediction of market trends has attracted much attention since the last century
We propose an network autoregressive (NAR)-GARCH model to describe the important features inherent in each stock index return and capture the joint effects among different nonsynchronous return processes simultaneously
The dynamics of each index return process are marginally depicted by a conventional time series model, which can be obtained by performing many software programs
Summary
The prediction of market trends has attracted much attention since the last century. Market participants make investment decisions according to their prediction of market trends. Thanks to the rapid development of information and communication technologies, market participants have opportunities to receive online information, such as the latest closing prices of global stock indices, updates on significant world events, and the newest economic policies announced by the most influential countries in the world This real-time information has affected financial market trends, especially causing large shocks in stock indices. The two return processes have similar patterns, which indicates that the S&P 500 index returns did show their leading effects on the AORD returns, especially for most of those returns having large volatilities, during this specific time period This type of relationship between different markets changes dynamically, which increases the difficulty of implementing the latest and helpful information into the timely prediction of market
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
