A study on the estimation and prediction of volatility on financial assets
Keywords:Log yield, Volatility, Portmanteau-Q test, Lagrange Multiplier test, AR(p)-ARCH(q)
Volatility in financial markets due to changes in the internal and external financial market environment causes economic entities to increase uncertainty of economic activity, thus affecting the real economy. The volatility of stock index, interest rate, and exchange rate has a negative impact on the business performance of companies and financial institutions due to decline in the value of stocks, bonds, and derivatives held for short-term trading purposes. In this study, therefore, the KRW/USD exchange rate and the KOSDAQ index data from January 2005 to December 2017 were converted to log yield data for volatility estimation. Autocorrelation test of the error terms confirmed the partial autocorrelation function, and a Portmanteau Q-test was performed. Significant parameters were estimated by the stepwise autoregressive method. The Lagrange Multiplier test (L-M test) was used for the ARCH effect and the order of the model, and parameters were estimated by the Maximum Likelihood Method. Fit of the estimated model was found to follow the white noise according to the Portmanteau Q-test using standardized residuals. As the result, AR(1,2,3,13)-ARCH(1) model was selected as the volatility estimation model for KRW/USD exchange rate, and AR(1)-ARCH(1) model for KOSDAQ index.
 Anderson T G and Bollerslev T (1998), Answering the skeptics: yes, standard volatility models do provide accurate forecasts, International Economic Review 39, 885-905.
 Akgiray V (1989), Conditional heteroskedasticity in time series of stock return evidence and forecasts, Journal of Business 62, 55-80.
 Jorion (1995), Predicting Volatility in the foreign exchange market, Journal of Finance 50, 507-528.
 Ghysels E, Santa-Clara P, Valkanov R (2003), Predicting volatility: the most out of return data sampled at different frequencies.
 Xiao and Aydemir (2007), Abdurrahman, Volatility Modelling and Forecasting in Finance, Knight J and Satchell S.(eds) (2007), Forecasting Volatility in the Financial Markets 3rd , Elsevier, pp.1-45.
 Kim T Y and Kwon O J (2001), Confidence interval forecast of exchange rate based on bootstrap method during economic crisis, Journal of Korean Data and Information Science Society 22, 895-902.
 Kim B and Kim J (2012), Time series models for daily exchange rate data, The Korean Journal of Applied Statistics 26, 1-14.
 ] Kim C (2013), Forecasting and long memory exchange rate volatility, Review of Business & Economics 26, 49-66.
 Jang D (2013), Exploratory data analysis for Korean daily exchange rate data with recurrence plots, Journal of Korean Data and Information Science Society 24, 1103-1112.
 Kwon D and Lee T (2014), Hedging effectiveness of KOSPI200 index futures throuth VECM-CC-GARCH model, Journal of Korean Data and Information Science Society 25, 1449-1466.
 ] Lee W and Chun H (2016), A deep learning analysis of the Chiness Yuanâ€™s volatility in the on share and offshore markets, Journal of Korean Data and Information Science Society 27, 327-335.
 Engle RF (1982), Autoregressive Conditional Heteroskedasticity with Estimates of the Variance of the United Kingdom Inflation, Econometrica 50, 987-1007.
 Bollerslev Tim (1986), Generalized Autoregressive Conditional Heteroskedasticity, Journal of Econometrics 31, 307-327.
 Ljung W K and Box G E P (1978), On a measure of lack of fit in time series model, Biometrika 65, 297-303.
 Engle RF, Granger CWJ, Kraft D (1984), Combining Competing Forecasts of Inflation Using a Bivariate ARCH Model, Journal of Economic Dynamics and Control 8, 151-165.