A TEST ON GARCH-TYPE MODELS OF THE S&P 500 INDEX

Open Access
Author:
Jiang, Shu
Area of Honors:
Economics
Degree:
Bachelor of Science
Document Type:
Thesis
Thesis Supervisors:
  • Andrew Ronald Gallant, Thesis Supervisor
  • James R. Tybout, Honors Advisor
Keywords:
  • S&P 500
  • GARCH
  • forecasting comparison
  • loss function
Abstract:
Forecasts of the future financial market are crucial for investment decisions such as asset pricing, hedging strategies and risk management. Since late 2013, the S&P 500 Index has experienced a sharp increase as the whole market seemed to recover from the last financial crisis. Investors who forecast this increase will be able to take a preemptive opportunity. Additionally, governments can make up policies to prevent the market from becoming overheated. In this thesis, I will use different GARCH-type models to make predictions and compare them with different loss functions and information criteria. After the comparison, the best model under every assumption will be selected by each loss function and information criteria. The conclusion is about the result analysis and future expectation.