Forecasting Financial Data with ARIMA and ARCH Models: The Case of Turkey


Degirmenci N., Akay A.

ESKISEHIR OSMANGAZI UNIVERSITESI IIBF DERGISI-ESKISEHIR OSMANGAZI UNIVERSITY JOURNAL OF ECONOMICS AND ADMINISTRATIVE SCIENCES, vol.12, no.3, pp.15-36, 2017 (Journal Indexed in ESCI) identifier

  • Publication Type: Article / Article
  • Volume: 12 Issue: 3
  • Publication Date: 2017
  • Title of Journal : ESKISEHIR OSMANGAZI UNIVERSITESI IIBF DERGISI-ESKISEHIR OSMANGAZI UNIVERSITY JOURNAL OF ECONOMICS AND ADMINISTRATIVE SCIENCES
  • Page Numbers: pp.15-36

Abstract

The aim of this study is to predict the stock market, gold, foreign exchange and oil prices with Box-Jenkins and ARCH models. In this direction, weekly datasets are used of BIST100 index, gold and oil prices and exchange rate variables between 01.02.2009-11.25.2016. As a result of the analyses, asymmetric effect is revealed in all variables except gold prices. Also, the predictions obtained from the ARCH models were found to be close to zero in the theil statistics.