:, CBOT DCE ( ) :, ,,,,,, ,, , % %,, 2001, 2004,,,,,,,,,

Size: px

Start display at page:

Download ":, CBOT DCE ( ) :, ,,,,,, ,, , % %,, 2001, 2004,,,,,,,,,"

酌索
7 years ago
Views:

1 3 ( ) ( 14853) ( ),, :, 2004 CBOT ( ) DCE ( ) CBOT DCE, 2004 CBOT DCE,, CBOT DCE,, CBOT DCE, DCE CBOT, W TO,, % %,,,,,, :,,,,,,,,, 4 3 CP I

2 :, CBOT DCE ( ) :, ,,,,,, ,, , % %,, 2001, 2004,,,,,,,,, :,, 8,, 2,,,,, 60%,,,,,,,,,, ( ), :,, ;,,,,,,, 5

3 ,,,,,,,,,, 3,,,,,,,,,,,,,,,,,,,,,,,,,,,,,,, 2004, 2003, , ,,, 97 64,, 80%,,, (, 2008),,, CBOT DCE,,,, (2006) (2004),, DCE CBOT,, CBOT, (2000) , ; ( 2007) 6

4 : (2008), CBOT,, CBOT,,,, ( Granger),,, ( ),,, :,, ;,, i, i, VAR,,,, VEC Granger,,,,, x y,,,, 3 :,,,, ; ; ( ),,,,,, (A simakopoulos, Ayling et al1, 2000; Chen and L in, 2004; Gour vitch, Bouquin Jeann s et al1, 2006) 1992 Baek B rock, (Baeck and B rock, 1992) 1994, H iem stra Jones, H2J : 11 {X t }, { Y t }, X m t X Lx t - Lx {X t } m L x, Y m t Y Lx t - Lx X m t = (X t, X t+1,, X t+m - 1 ) Y m t = ( Y t, Y t+1,, Y t+m - 1 ) X L x t- L x = (X t- L x, X t- L x +1,, X t- 1 ) Y L x t- L x = ( Y t- L x, Y t- L x +1,, Y t- 1 ) m = 1, 2, 3, L x = 1, 2, 3, L y = 1, 2, 3 m, Lx, Ly, e > 0, : 7

5 Pr( X m t - X m s < e X L x t- L x - X L x s- L x < e, Y L y t- L y - Y L y s- L y < e) = Pr( X m t - X m s < e X L x t- L x - X L x s- L x < e) (3), Pr( ), ( supremum norm), e : {Y t } {X t } Granger : Lx Xt, m Xt, Ly Yt (Chen and L in, 2004;Diks and Panchenko, 2006), Yt Xt H iem stra Jones (3) : C1 (m + L x, L y, e) Pr(X m +L x t- L x - X m +L x s- L x < e, Y L y t- L y - Y L y s- L y < e) C2 (L x, L y, e) Pr(X L x t- L x - X L x s- L x < e, Y L y t- L y - Y L y s - L y < e) C3 (m + L x, e) Pr(X m +L x t- L x - X m +L x s- L x < e) C4 (L x, e) Pr(X L x t- L x - X L x s - L x < e), (3) (H iem stra and Jones, 1994) : C1 (m + L x, L y, e) C2 (L x, L y, e) = C3 (m + L x, e) C4 (L x, e), : C^1 (m + L x, L y, e, n) 2 n ( n - 1) I( xm +Lx t- Lx, x m +Lx s- Lx, e) I( y Ly t- Ly, y Ly s- Ly, e) t < s C^2 (L x, L y, e, n) 2 n ( n - 1) t < s I( xlx t- Lx, x Lx s- Lx, e) I( y Ly t- Ly, y Ly s- Ly, e) C^3 (m + L x, e, n) 2 n ( n - 1) I( xm +Lx t- Lx, x m +Lx s- Lx, e) t < s C^4 (L x, e, n) 2 n ( n - 1) t < s I( xlx t- Lx, x Lx s- Lx, e), I( Z 1, Z 2, e), Z1 Z2 (Maximum2norm distance) e, I 1, 0 n H iem stra Jones : : = C^1 (m + L x, L y, e) C^2 (L x, L y, e) - C^3 (m + L x, e) C^4 (L x, e) (4) (5) (6), N (0, 2 (m, L x, L y, e) ) (7), 2007 (Monte2Carlo),, (Lu, 2007),,,, : 1000 N (0, 1) { Zt}, 1000 { Zt} { Yt}, {Xt},, { Zt},, 1000 z (m, Lx, Ly, e) z (m, Lx, Ly, e) 8,,

6 : 3 : (1) ; (2) ; (3) (Non2parametric Method),,,,,,,, ( ) e, e,,, e (Baeck and B rock, 1992; H iem stra and Jones, 1994),,, e,,,, e,,, e H iem stra Jones ( 1994) e = 115,, e ( ), : ; : ; : DCE CBOT,,,,,,,,,,,,, 3 : ,, : 1996 ; 2004,, 2004,,, 2004, , , 2002,, CBOT DCE 4 3 DCE, 9

7 ,, DCE CBOT ;, DCE,, DCE 4, : CBOT DCE CBOT CBOT DCE ;, 4, : CBOT DCE CBOT CBOT DCE ( ),,, 1, CBOT DCE,,,, = C1 (m +L x, L y, e) C2 (L x, L y, e) - C3 (m +L x, e) C4 (L x, e), / ( Intensity of Causality), /, 3, 80% 90% 95%, Lx =Ly, 1 12, 12 (Chen and L in, 2004) : H 0 a: A B A B A B H 0 b: B A B A % 90% 95%, ( ),, 2004 CBOT DCE, CBOT DCE, DCE CBOT ; 2004 CBOT DCE, CBOT DCE, : CBOT DCE 12, DCE CBOT , DCE 7, DCE 3 ; CBOT 12, CBOT ,, DCE,,,, ; 2004,, DCE, CBOT, 2004, DCE 10

8 : CBO T DC E CBO T DC E CBO T DC E CBO T CBO T, CBOT, CBOT DCE : CBOT DCE 1 12, DCE CBOT

9 DC E CBO T DC E CBO T CBO T CBO T DC E DCE , CBOT, 1 12 CBOT 10 11, 1 8 DCE, CBOT, CBOT DCE, 12

10 : 1 12 ; CBOT CBOT 1 1 7, CBOT DCE CBOT, DCE,, ( ),,,, DCE,, CBOT,,,,,,,, ( ),,, 2009,,,,,,, ( ),,,,,,,,,,,,, 11 A simakopoulos, I1, Ayling, D1, and MansorMahmood, W1, Non2linear Granger causality in the currency futures returns, Econom ics Letters, 2000, Vol168:

11 21Baeck, E1 G1, and B rock, W1 A1, 1992, A Nonparametric Test for Independence of a Multivariate Time Series, Statistica Sinica 2, 1992, Vol12: Chen, A12S1, and L in, J1 W1, Cointegration and detectable linear and nonlinear causality: analysis using the London Metal Exchange lead contract, App lied Econom ics, 2004, Vol136: D iks, C1, and Panchenko, V1, A new statistic and practical guidelines for nonparametric Granger causality testing, Journal of Econom ic Dynam ics and Control, 2006, Vol130: Gour vitch, B1, Bouquin Jeann s, R1, and Faucon, G1, L inear and nonlinear causality between signals: methods, examples and neu2 rophysiological app lications, B iological Cybernetics, 2006, Vol195: Granger, C1 W1 J1, Investigating Causal Relations by Econometric Models and Cross2spectral Methods, Econometrica, 1969, Vol137: H iem stra, C1, and Jones, J1 D1, Testing for L inear and Nonlinear Granger Causality in the Stock Price2Volume Relation, Journal of Fi2 nance, 1994, Vol149: Lu, J1,Master Thesis for Economics, Cornell Univesity, , 2003 (3) , 2008 (4) , 2008 (10) 121, 1 1 ( ), 2008 (01) 131, 1 1, 2006 (2) 141, 1 1, 2006 (1) 151, 1 VAR 1, 2007 (1) 14

(156) / Spurious Regression Unit Root Test Cointergration TestVector Error Correction Model Granger / /

(156) / Spurious Regression Unit Root Test Cointergration TestVector Error Correction Model Granger / / (155) * ** / / / / 1973 ~1974 1979 ~1980 1987 ~1989 * ** (156) 1990 2004 1997 1996 1980 / Spurious Regression Unit Root Test Cointergration TestVector Error Correction Model Granger / / (157) Hedonic Price