- 1 -

Size: px

Start display at page:

Download "- 1 -"

홍기 용
5 years ago
Views:

1 - 1 -

2 External Shocks and the Heterogeneous Autoregressive Model of Realized Volatility Abstract: We examine the information effect of external shocks on the realized volatility based on the HAR-RV (heterogeneous autoregressive realized volatility) model in Korean stock market. For the study, we estimate the realized volatility using the five minute intraday high-frequency KOSPI return data from Jan to June And we develop and use the single external shock variable (ES) which is constructed from the 10-external shock variables representing changes of international stock, crude oil, gold, foreign exchange market prices, and interest rate. We use factor analysis to develop the ES from the 10-external shock variables. The main results are as follows. First, the developed external shock variable (ES) represents well the shocks in international market prices and the time-series patterns of ES are similar to the realized volatility patterns of KOSPI, especially in the market crash period. Second, in In-sample analysis using the HAR-RV-ES model which is the model added the ES variable to HAR-RV model as a new explanatory variable, the ES variable shows a significant explanatory power on changes of daily and weekly realized volatility. Third, in Out-of-sample analysis, the ES variable has a significant predictive power on future realized volatility. Fourth, The information effects of ES variable are robust to volatility leverage effect. These results suggest that the developed ES variable in this study is useful variable with additive and independent information effect for explaining and predicting the future volatility in the HAR-RV model, and the proposed method for developing the ES variable is helpful for the improvement of HAR-RV model. Keywords: External shock variable, Realized Volatility, Heterogenous autoregressive model, Factor analysis, In-sample and Out-of-sample - 2 -

3 - 3 -

4 - 4 -

5 - 5 -

6 - 6 -

7 - 7 -

8 - 8 -

9 - 9 -

10 - 10 -

11 ln ln ln

12 max

13 - 13 -

14 - 14 -

15 - 15 -

16 - 16 -

17 - 17 -

18 - 18 -

19 - 19 -

20 - 20 -

21 - 21 -

22 - 22 -

23 - 23 -

24 - 24 -

25 min

26 - 26 -

27 - 27 -

28 - 28 -

29 - 29 -

30 - 30 -

31 - 31 -

32 - 32 -

33 - 33 -

34 - 34 -

35 - 35 -

36 - 36 -

37 - 37 -

38 실현변동성 ( ) 연속요소 () 점프요소 () 평균 표준편차 왜도 첨도 최댓값 % 분위수 중위수 % 분위수 최솟값 Ljung-Box

39 USD/EUR USD/JPY USD/CNY S&P500 Nikkei225 평균 표준편차 왜도 첨도 Ljung-Box ShangHai EFFR WTI Gold CRB 평균 표준편차 왜도 첨도 Ljung-Box

40 USD/EUR USD/JPY USD/CNY S&P500 Nikkei225 요인부하량 ShangHai EFFR Oil WTI Gold CRB 요인부하량

41 - 41 -

42 HAR-RV-J 모형 HAR-RV-J-ES 모형 [ 종속변수기간구분 ] [ 종속변수기간구분 ] 일별주별월별일별주별월별 a (7.03) a (5.10) a (3.97) a (-8.01) a (3.86) a (2.69) a (4.39) a (-3.93) (1.13) a (2.80) (1.12) b (-1.99) a (6.40) a (5.57) a (4.07) a (-7.74) a (-4.83) a (4.24) a (2.84) a (4.20) a (-4.17) a (-2.78) (1.13) a (2.73) (1.32) b (-2.00) (-0.79) 값 조정 64.54% 78.86% 64.58% 65.44% 79.89% 64.80%

43 일별 [n=1,861] Panel A: 비교모형 (HAR-RV-J 모형 ) 주별 [n=372] 월별 [n=84] MAE RMSE Min.Zar.R % 50.11% 48.17% Panel B: 제안모형 (HAR-RV-J-ES 모형 ) MAE RMSE Min.Zar.R % 49.04% 49.21% Panel C: 제안모형의예측우수성평가 Theil s U MSE-F l a ENC-NEW a a c

44 LHAR-RV-J모형 LHAR-RV-J-ES모형 [ 종속변수기간구분 ] [ 종속변수기간구분 ] 일별 주별 월별 일별 주별 월별 Panel A: 내표본에서의모형추정 a a a a (4.48) (4.01) (0.76) (4.44) (4.17) (0.80) a a a a a a (5.17) (3.35) (3.04) (5.28) (3.28) (2.80) a a a a (3.53) (4.00) (0.83) (3.56) (3.90) (0.96) a a b a a b (-7.13) (-5.04) (-1.97) (-7.01) (-5.08) (-1.99) a a a a (-6.62) (-2.95) (-0.33) (-5.52) (-2.74) (-0.21) a a (-2.75) (-1.23) (-0.80) (-2.94) (-1.44) (-0.78) (-0.42) (-0.86) (-0.62) (-0.30) (-0.68) (-0.66) a a (-3.35) (-2.29) (-0.66) 값 조정 66.55% 81.49% 65.49% 66.91% 81.89% 65.64% Panel B: 외표본에서의모형예측력평가 MAE RMSE M.Z.R % 51.78% 48.73% 52.45% 51.45% 50.12% [ 일별 ] [ 주별 ] [ 월별 ] Theil U MSE-F a E.-NEW a a a

45 외부충격자료 인과관계 : 전체기간 관심기간 F-값 F-값 검색어를통해확인된 네이버트렌드의관심기간 USD/EUR a ~ USD/JPY a ~ USD/CNY a ~ S&P a ~ Nikkei a ~ ShangHai b a ~ EFFR a a ~ WTI b ~ Gold b ~ CRB a ~

46 LHAR-RV-CJ모형 LHAR-RV-CJ-ES모형 [ 종속변수기간구분 ] [ 종속변수기간구분 ] 일별 주별 월별 일별 주별 월별 Panel A: 내표본에서의모형추정 a a a a (6.02) (4.04) (0.58) (5.50) (4.34) (0.58) a a a a a a (3.51) (3.80) (2.62) (3.88) (3.65) (2.63) (1.10) (0.79) (-0.57) (1.14) (1.34) (-0.53) a (1.06) (2.95) (-0.88) (0.78) (3.22) (-0.91) b b (2.03) (0.28) (-0.24) (1.99) (0.59) (-0.33) a b a b (2.56) (2.05) (1.54) (2.71) (2.11) (1.57) a a (-4.96) (-3.59) (-0.84) 값 조정 65.26% 79.52% 67.62% 66.18% 80.36% 67.84% Panel B: 외표본에서의모형예측력평가 MAE RMSE M.Z.R % 50.83% 48.67% 51.49% 49.99% 50.29% [ 일별 ] [ 주별 ] [ 월별 ] Theil U MSE-F a E.-NEW a a a

47 LHAR-RV-CJ모형 LHAR-RV-CJ-ES모형 [ 종속변수기간구분 ] [ 종속변수기간구분 ] 일별 주별 월별 일별 주별 월별 Panel A: 내표본에서의모형추정 a a a a (3.56) (4.14) (0.25) (3.56) (4.54) (0.31) a a a a a a (4.25) (3.86) (3.12) (4.39) (3.77) (3.20) c b (1.36) (1.74) (-0.62) (1.41) (2.06) (-0.61) (-1.42) (0.31) (-0.78) (-1.29) (0.46) (-0.72) (1.42) (0.80) (-0.31) (1.34) (0.94) (-0.40) b b b b (2.24) (2.10) (1.23) (2.32) (2.10) (1.26) a a a a (-7.12) (-3.18) (0.16) (-6.01) (-2.84) (0.24) b a (-2.47) (-1.14) (-0.79) (-2.66) (-1.32) (-0.77) (-1.19) (-1.24) (-0.87) (-1.10) (-1.08) (-0.92) a a (-3.53) (-2.62) (-0.78) 값 조정 67.27% 81.95% 68.49% 67.64% 82.29% 68.70% Panel B: 외표본에서의모형예측력평가 MAE RMSE M.Z.R % 52.42% 49.89% 52.08% 52.19% 51.59% [ 일별 ] [ 주별 ] [ 월별 ] Theil U MSE-F a E.-NEW a a a

지능정보연구제 16 권제 1 호 2010 년 3 월 (pp.71~92),.,.,., Support Vector Machines,,., KOSPI200.,. * 지능정보연구제 16 권제 1 호 2010 년 3 월

지능정보연구제 16 권제 1 호 2010 년 3 월 (pp.71~92),.,.,., Support Vector Machines,,., 2004 5 2009 12 KOSPI200.,. * 2009. 지능정보연구제 16 권제 1 호 2010 년 3 월 김선웅 안현철 社 1), 28 1, 2009, 4. 1. 지능정보연구제 16 권제 1 호 2010 년 3 월 Support