Out-of-Sample Forecasting Performance of Won/Dollar Exchange Rate Return Volatility Model (원-달러환율의 실시간 변동성 예측모형간 비교)

33 Pages Posted: 4 Dec 2017

Date Written: June 30, 2009

Abstract

English Abstract: We compare the out-of-sample forecasting performance of volatility models using daily exchange rate for the KRW/USD during the period from 1992 to 2008. For various forecasting horizons, historical volatility models with a long memory tend to make more accurate forecasts. Especially, we carefully observe the difference between the EWMA and the GARCH (1,1) model. Our empirical finding that the GARCH model puts too much weight on recent observations relative to those in the past is consistent with prior evidence showing that asset market volatility has a long memory, such as Ding and Granger (1996). The forecasting model with the lowest MSFE and VaR forecast error among the models we consider is the EWMA model in which the forecast volatility for the coming period is a weighted average of recent squared return with exponentially declining weights. In terms of forecast accuracy, it clearly dominates the widely accepted GARCH and rolling window GARCH models.

We also present a multiple comparison of the out-of-sample forecasting performance of volatility using the stationary bootstrap of Politis and Romano (1994). We find that the White's reality check for the GARCH (1,1) expanding window model and the FIGARCH (1,1) expanding window model clearly reject the null hypothesis and there exists a better model than the two benchmark models. On the other hand, when the EWMA model is the benchmark, the White's for all forecasting horizons are very high, which indicates the null hypothesis may not be rejected. The Hansen's report the same results. The GARCH (1,1) expanding window model and the FIGARCH (1,1) expanding window model are dominated by the best competing model in most of the forecasting horizons. In contrast, the RiskMetrics model seems to be the most preferred.

We also consider combining the forecasts generated by averaging the six raw forecasts and a trimmed set of forecasts which calculate the mean of the four forecasts after disregarding the highest and lowest forecasts from the six models. This experiment confirms that the forecast combinations always outperform forecasts from a single model.

Korean Abstract: 1992-2008년간의 일별 대미달러 원화환율시계열에 비모수적 조정과정을 통한 Inclan and Tiao 통계량을 이용하여 구조적 변화를 검정하였다. 원화의 대미달러 일별 환율의 변화는 통계적으로 유의미한 구조적 변화를 겪지 않은 것으로 나타났다.

벤치마크 모형에 의해 생성된 환율수익률 변동성의 표본외 예측력을 비교모형에 의한 예측치와 비교함으로써 환율의 변동성을 예측하기 위한 최적모형을 구축하고자 하였다. 벤치마크 모형으로는 선행연구에서 사용된 바 있는 확장창 GARCH(1,1)모형 (expanding window GARCH(1,1))과 조건부 이분산성의 장기기억프로세스적인 특성을 보다 잘 포착할 수 있는 FIGARCH(1,d,1)모형 등을 사용하였으며, 환율수익률 변동성의 예측력에 있어서 벤치마크 모형과 비교할 모형으로는 환율수익률 비조건부 분산 시계열의 구조적 변화를 고려할 수 있는 rolling window GARCH(1,1)모형을 이용하였다. 본 연구에서는 다양한 변동성 예측모형 간의 예측력 비교를 위하여 2가지 손실함수(loss function)를 사용하였는데, 먼저 Starica and Granger (2005)와 Starica et al. (2005)의 누적MSFE (aggregated version of mean squared forecasting error)를 사용하였으며, 두 번째 손실함수로서 Gonzales-Rivera et al. (2004)의 VaR 손실함수를 사용하였다. 표본외 예측력 분석결과, 역사적 변동성 모형 중에서 변동성의 장기기억특성을 고려하여 과거 관찰치에 대한 가중치가 GARCH 타입의 변동성 예측모형보다 서서히 감소하도록 설계된 EWMA (exponentially weighted moving average)모형의 변동성 예측가능성이 통계적으로 유의미하게 높은 것으로 나타나 대미달러 원화환율수익률의 변동성이 분산시계열의 구조적 변화를 고려하는 단기기억모형의 특성보다는 장기기억특성을 가지고 있음을 확인할 수 있었다.

Keywords: Parameter Instability, Volatility Break, Exchange Rate Change, ICSS Algorithm, White Reality Check Test, Hansen SPA Test, GARCH, EWMA, Long Memory Process

JEL Classification: F31, F33

Suggested Citation

Lee, Hojin, Out-of-Sample Forecasting Performance of Won/Dollar Exchange Rate Return Volatility Model (원-달러환율의 실시간 변동성 예측모형간 비교) (June 30, 2009). East Asian Economic Review, Vol. 13, No. 1, pp. 57-88, June 2009, Available at SSRN: https://ssrn.com/abstract=3077801 or http://dx.doi.org/10.2139/ssrn.3077801

Hojin Lee (Contact Author)

Myongji University ( email )

50-3 Namgajwadong
Seodaemungu
Seoul, 120-728

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
25
Abstract Views
285
PlumX Metrics