2013 2013 Chuyên ngành: Tài 60340201 ngân hàng L u c a riêng Các s li u, k t qu nêu lu c công b b t k cơng trình khác Tác gi nh Giao M CL C TRANG PH BÌA L M CL C DANH M C T VI T T T DANH M C B NG DANH M C HÌNH V GI I THI U 1.1 Lý ch tài 1.2 M c tiêu nghiên c u 1.3 V nghiên c u 1.4 u 1.5 N i dung nghiên c u 1.6 c ti n c tài T NG QUAN CÁC NGHIÊN C 2.1 Các nghiên c kh giá h 2.2 Các nghiên c mơ hình ti n t nh t giá h NH T GIÁ H 16 NT 3.1 Thành ph n c n t 16 3.1.1 T giá h c ngo i sinh 16 3.1.2 Mơ hình c nv 3.2 Mơ hình ti n t 3.3 nh giá 17 19 nt CÁC V nh t giá h i V KINH T ng 21 NG 24 4.1 ng d ng tài 24 4.2 ng cho Vi t Nam 27 4.2.1 Ki 4.2.2 L a ch nh tính d ng 28 tr phù h p 29 4.2.3 Ki ng liên k c tính m i quan h dài h n 29 4.2.4 nh m c th i ng n h n 30 4.3 L a ch n bi d li u ph c v phân tích 31 CHÍNH SÁCH T GIÁ H VI T NAM 35 5.1 37 5.2 40 5.3 n 43 K T QU TH C NGHI M 48 6.1 Ki nh tính d ng 48 6.2 L a ch tr cho mơ hình VAR 48 6.3 Ki ng liên k t m i quan h dài h n c a mơ hình ti n t nh t giá h 6.4 Mơ hình SVAR m 49 c th i gi a bi n hi u l c c a mơ hình MAER ng n h n 55 K T LU N 60 TÀI LI U THAM KH O PH L C DANH M C T VI T T T ADF Augmented Dickey Fuller ECM Error Correction Model FED Ngân hàng D tr Liên bang Hoa K MAER nt NHNN nh t giá h c Vi t Nam NHTM Ngân hàng th gm i PPP Ngang giá s c mua SVAR Structural Vector Autoregression TCTD T ch c tín d ng VAR Vector Autoregression USD VECM VND Vector Error Correction Model ng Vi t Nam DANH M C B NG B ng 3.1: D báo c t lõi c nt nh t giá h 21 1: Các bi n mô hình 32 B ng 5.1 giao d ch t giá t B ng 6.1: Ki nh tính d ng c a s li u (sai phân b c 1) 48 B ng 6.2: Ki B n 35 tr t a mô hình theo tiêu chu n 49 ng liên k c chu n hóa 49 B ng 6.4: K t qu mơ hình VECM 50 B ng 6.5: K t qu ki nh ph mơ hình VECM 54 B ng 6.6: K t qu mơ hình SVAR 54 B ng 6.7: K t qu ki nh ph mơ hình SVAR 57 DANH M C HÌNH V Hình ng c a cung ti n t giá h Hình 5.1 T Hình 5.2: Bi Vi t Nam 1999 ng t 2013 36 2009 38 Hình 5.3: T giá th c t giá th n 2009 20 ng t theo ngày VND/USD giai 2011 41 Hình 5.4: Di n bi n t 45 Hình 5.5: Di n bi n t 47 GI I THI U 1.1 Lý ch tài: nh t giá v n m t v quan tr i v i c nhà kinh t t bi n v giá quan tr ng n n kinh t , t giá h c hi n vai trò c a m t neo danh trì kh nh tranh qu c t T giá h ng m nh m tri n sau th i k Bretton ng kinh t s phát Woods Trong ba th p k qua, m t s nh t m quan tr ng c trì s chính: s m t giá c n ng thái t giá h nh c a n n kinh t b i c giá h c c i tồn c u t hóa tài ng M Latinh th p niên 80, cu c kh ng ho ng t Anh Tây Ban Nha nh i Mexico, s s s c kh ng ho ng kinh t c a chu n ti n t (currency board) gi m giá c so v Argentina, ng Euro th i gian qua Nghiên c u th c nghi m v kinh t t giá h s nhân th s ng có th m i quan tâm to l n v s c a h th ng Bretton giá h i v i ho T bi c phát tri n theo c p Woods, s c n thi ng c a t ng kinh t c a qu c gia b i c nh kinh t hi n m th c nghi m trên, hành vi c a t giá h ng khó câu h i v vi ng c a m t s ng l c m nh m cho h c gi nh th c nghi m c a t giá h ng n lai Trên th c t , nhà kinh t h u hành sách tính tốn, d báo t giá h ng quy t sách phù h p v i tình hình c a t ng qu c gia Tuy nhiên, li u có th t s có kh n giá h r t nhi y, mơ hình d giá h t s có hi u qu n n kinh t m i n i? T m quan tr ng c a n n kinh t m i n kinh t th gi i iv in n c l i không nh c s quan tâm to l n n kinh t cơng nghi p hóa Và nghiên c u góp ph n vào vi c nghiên c u Vi t Nam c p thi m t nh ng n n kinh t m i n i v v nh t giá h u hành h p lý 1.2 M c tiêu nghiên c u: M c tiêu c a nghiên c u nh t giá h ki m tra tính h p l c a mơ hình ti n t VND/USD Vi t Nam n 1999 ng th i, nghiên c u khơng ch tìm ki m b ng ch ng th c nghi tin c y h tr hi u l c ng n h n mà dài h n c MAER cho t giá h 1.3 V Nh ng v USD nghiên c u: mà nghiên c u tìm cách tr l i bao g m: (1) Mơ hình ti n t gi i thích s bi ng c a t giá h th nào? (2) Có t n t i m i quan h b n ng liên k t gi a t giá y u t ti n t Vi t Nam? (3) Có s phù h p v m t lý thuy t c a h s 1.4 Bài nghiên c u d ng hay không? u: ng c a nghiên c u c a Eduardo Loría, Armando Sánchez, Uberto Salgado, (2010) approach of exchange rate determination in Mexico 1994 2007: A cointegrated Ph l c B: K t qu ki nh tính d ng c a bi n s mơ hình Bi n ADF PP KPSS e 0,48907 0,553021 0,840450 -7,908713 -7,907257 0,219110 -2,105863 -2,090809 0,943637 -5,695693 -5,625962 0,308915 -0,260799 -0,262010 0,928278 -5,730010 -5,712664 0,077307 -0,477832 -1,209524 0,926562 -2,859346 -33,05032 0,279156 -1,575501 -1,752666 0,885241 -4,797769 -4,706312 0,226131 -2,453498 -2,053384 0,573002 -5,294289 -5,075508 0,151815 -1,117420 -0,846285 0,637810 -4,308831 -4,385299 0,093888 m m* y y* i i* Ph l c C: K t qu ki tr t n VAR Lag Order Selection Criteria Endogenous variables: E CLM CLY CLI Exogenous variables: C Date: 06/25/14 Time: 20:39 Sample: 58 Included observations: 54 Lag LogL LR FPE 167.4671 483.0043 514.3231 533.2216 604.9623 NA 572.6417 52.19797 28.69772 98.31136* 2.76e-08 4.20e-13 2.41e-13 2.22e-13 2.96e-14* AIC SC -6.054336 -5.907004 -17.14831 -16.41165 -17.71567 -16.38968 -17.82302 -15.90770 -19.88749* -17.38285* HQ -5.997516 -16.86421 -17.20429 -17.08436 -18.92155* * indicates lag order selected by the criterion LR: sequential modified LR test statistic (each test at 5% level) FPE: Final prediction error AIC: Akaike information criterion SC: Schwarz information criterion HQ: Hannan-Quinn information criterion Ghi chú: E, CLM, CLY, CLI l t bi n (e), (m m*), (y y*), (i Ph l c D: K t qu ki nh m i quan h i*) mơ hình ng liên k t mơ hình VECM K t qu ki nh m i quan h ng liên k t: Date: 06/25/14 Time: 20:41 Sample (adjusted): 2000Q2 2013Q2 Included observations: 53 after adjustments Trend assumption: Linear deterministic trend Series: E CLM CLY CLI Exogenous series: DUMMY D1 D2 D3 Warning: Critical values assume no exogenous series Lags interval (in first differences): to Unrestricted Cointegration Rank Test (Trace) Hypothesized No of CE(s) Eigenvalue None * At most * At most At most 0.479818 0.306229 0.217779 0.001412 Trace Statistic 0.05 Critical Value Prob.** 67.10972 32.47019 13.09269 0.074906 47.85613 29.79707 15.49471 3.841466 0.0003 0.0240 0.1114 0.7843 Trace test indicates cointegrating eqn(s) at the 0.05 level * denotes rejection of the hypothesis at the 0.05 level **MacKinnon-Haug-Michelis (1999) p-values Unrestricted Cointegration Rank Test (Maximum Eigenvalue) Hypothesized No of CE(s) Eigenvalue Max-Eigen 0.05 Statistic Critical Value Prob.** None * At most At most At most 0.479818 0.306229 0.217779 0.001412 34.63953 19.37750 13.01778 0.074906 27.58434 21.13162 14.26460 3.841466 0.0053 0.0864 0.0779 0.7843 Max-eigenvalue test indicates cointegrating eqn(s) at the 0.05 level * denotes rejection of the hypothesis at the 0.05 level **MacKinnon-Haug-Michelis (1999) p-values Unrestricted Cointegrating Coefficients (normalized by b'*S11*b=I): E 64.44100 134.1222 -0.813405 34.35422 CLM -37.58864 24.12820 11.76336 -0.606420 CLY 53.76667 -69.23053 -15.09410 7.078848 CLI -4.339822 1.068197 -2.330499 -3.321673 Unrestricted Adjustment Coefficients (alpha): D(E) D(CLM) D(CLY) D(CLI) -0.002631 0.000665 -0.007114 0.010444 Cointegrating Equation(s): -0.000904 -0.002349 -0.000207 -0.020530 -0.000820 -0.000637 0.002450 0.025867 Log likelihood 0.000120 -0.000197 -2.64E-05 0.001659 634.6608 Normalized cointegrating coefficients (standard error in parentheses) E CLM CLY CLI 1.000000 -0.583303 0.834355 -0.067346 (0.13322) (0.23636) (0.01687) Adjustment coefficients (standard error in parentheses) D(E) -0.169559 (0.05607) D(CLM) 0.042830 (0.08013) D(CLY) -0.458465 (0.10549) D(CLI) 0.673046 (0.93430) Ghi chú: E, CLM, CLY, CLI l t bi n (e), (m m*), (y y*), (i i*) mô hình K t qu mơ hình VECM: Vector Error Correction Estimates Date: 10/04/14 Time: 09:29 Sample (adjusted): 58 Included observations: 53 after adjustments Standard errors in ( ) & t-statistics in [ ] Cointegrating Eq: CointEq1 E(-1) CLM(-1) C 1.000000 -0.583303 (0.13322) [-4.37839] 0.834355 (0.23636) [ 3.53001] -0.067346 (0.01687) [-3.99228] -4.031254 Error Correction: D(E) D(CLM) D(CLY) D(CLI) CointEq1 -0.169559 (0.05607) [-3.02385] -0.275546 (0.17030) [-1.61801] 0.132171 (0.14967) [ 0.88309] 0.061213 (0.15103) [ 0.40530] 0.050024 (0.15381) [ 0.32523] -0.291860 (0.12129) 0.042830 (0.08013) [ 0.53451] 0.144024 (0.24336) [ 0.59181] 0.117129 (0.21388) [ 0.54765] -0.577112 (0.21582) [-2.67399] -0.597002 (0.21980) [-2.71613] 0.663650 (0.17333) -0.458465 (0.10549) [-4.34585] -0.291978 (0.32039) [-0.91131] 0.119789 (0.28158) [ 0.42542] 0.109615 (0.28414) [ 0.38578] -0.684399 (0.28937) [-2.36511] -0.554871 (0.22819) 0.673046 (0.93430) [ 0.72038] 0.096489 (2.83751) [ 0.03400] 3.138513 (2.49376) [ 1.25855] 2.438127 (2.51646) [ 0.96887] -2.109153 (2.56279) [-0.82299] -1.093352 (2.02093) CLY(-1) CLI(-1) D(E(-1)) D(E(-2)) D(E(-3)) D(E(-4)) D(CLM(-1)) D(CLM(-2)) D(CLM(-3)) D(CLM(-4)) D(CLY(-1)) D(CLY(-2)) D(CLY(-3)) D(CLY(-4)) D(CLI(-1)) D(CLI(-2)) D(CLI(-3)) D(CLI(-4)) C DUMMY [-2.40629] 0.057804 (0.07972) [ 0.72507] -0.004566 (0.08107) [-0.05632] 0.118718 (0.07216) [ 1.64522] 0.045147 (0.06618) [ 0.68223] 0.047304 (0.06247) [ 0.75722] -0.043670 (0.06615) [-0.66019] -0.097891 (0.06580) [-1.48762] -0.002774 (0.01015) [-0.27324] -0.006955 (0.00966) [-0.71970] 0.009038 (0.00956) [ 0.94558] -0.002249 (0.01060) [-0.21215] 0.000425 (0.01041) [ 0.04081] -0.004221 (0.00451) [ 3.82892] -0.151330 (0.11392) [-1.32834] 0.110963 (0.11585) [ 0.95780] -0.168294 (0.10312) [-1.63208] 0.108987 (0.09457) [ 1.15250] 0.109964 (0.08927) [ 1.23179] 0.154533 (0.09453) [ 1.63482] 0.126302 (0.09403) [ 1.34316] 0.013284 (0.01451) [ 0.91552] 0.013937 (0.01381) [ 1.00915] -0.025433 (0.01366) [-1.86201] -0.002564 (0.01515) [-0.16925] 0.035164 (0.01488) [ 2.36292] -0.013394 (0.00645) [-2.43162] -0.113999 (0.14999) [-0.76006] 0.053955 (0.15253) [ 0.35375] 0.073601 (0.13576) [ 0.54215] -0.148271 (0.12450) [-1.19093] -0.297492 (0.11753) [-2.53120] -0.330926 (0.12445) [-2.65917] 0.371778 (0.12380) [ 3.00306] -0.003659 (0.01910) [-0.19152] -0.014489 (0.01818) [-0.79691] 0.007481 (0.01798) [ 0.41599] -0.052864 (0.01995) [-2.65035] 0.050345 (0.01959) [ 2.56964] 0.013898 (0.00849) [-0.54101] 1.421525 (1.32833) [ 1.07016] 0.307935 (1.35081) [ 0.22796] -0.059563 (1.20231) [-0.04954] -0.423205 (1.10261) [-0.38382] 0.780961 (1.04089) [ 0.75029] 0.797383 (1.10215) [ 0.72348] 0.317446 (1.09641) [ 0.28953] 0.266342 (0.16918) [ 1.57435] -0.043128 (0.16102) [-0.26783] 0.478639 (0.15926) [ 3.00541] -0.179010 (0.17665) [-1.01337] -0.006110 (0.17351) [-0.03521] 0.170334 (0.07521) [-0.93508] 0.008329 (0.01833) [ 0.45433] 0.006725 (0.00838) [ 0.80288] 0.009686 (0.01924) [ 0.50337] [-2.07639] -0.039844 (0.02620) [-1.52086] -0.029527 (0.01197) [-2.46676] -0.034961 (0.02750) [-1.27145] [ 1.63657] -0.048627 (0.03449) [-1.40987] 0.004467 (0.01576) [ 0.28348] -0.034117 (0.03620) [-0.94245] [ 2.26479] 0.009001 (0.30546) [ 0.02947] -0.145822 (0.13957) [-1.04483] -0.016621 (0.32060) [-0.05184] 0.495747 0.154157 0.001244 0.006335 1.451292 207.2779 -6.991619 -6.173762 0.003300 0.006888 0.720082 0.530460 0.002540 0.009053 3.797458 188.3578 -6.277651 -5.459794 0.019227 0.013211 0.992083 0.986720 0.004403 0.011918 184.9820 173.7824 -5.727636 -4.909779 0.013078 0.103420 0.623916 0.369149 0.345368 0.105551 2.448967 58.18232 -1.365370 -0.547513 0.032985 0.132891 Determinant resid covariance (dof adj.) Determinant resid covariance Log likelihood Akaike information criterion Schwarz criterion 3.99E-15 4.67E-16 634.6608 -20.47777 -17.05764 D1 D2 D3 R-squared Adj R-squared Sum sq resids S.E equation F-statistic Log likelihood Akaike AIC Schwarz SC Mean dependent S.D dependent Ghi chú: E, CLM, CLY, CLI l t bi n (e), (m m*), (y y*), (i i*) mơ hình Ki nh tính d ng c a ph Null Hypothesis: ERESID has a unit root Exogenous: Constant, Linear Trend Bandwidth: (Newey-West automatic) using Bartlett kernel Adj t-Stat -7.699828 -4.130526 -3.492149 -3.174802 Phillips-Perron test statistic Test critical values: 1% level 5% level 10% level Prob.* 0.0000 *MacKinnon (1996) one-sided p-values Residual variance (no correction) HAC corrected variance (Bartlett kernel) 4.22E-05 4.61E-05 Phillips-Perron Test Equation Dependent Variable: D(ERESID) Method: Least Squares Date: 10/04/14 Time: 12:14 Sample (adjusted): 58 Included observations: 56 after adjustments Variable Coefficient ERESID(-1) C @TREND(1) -1.056447 1.18E-05 -3.41E-07 R-squared Adjusted R-squared S.E of regression Sum squared resid Log likelihood F-statistic Prob(F-statistic) 0.528177 0.510372 0.006681 0.002365 202.5594 29.66510 0.000000 Std Error t-Statistic 0.137155 -7.702587 0.001858 0.006370 5.52E-05 -0.006170 Mean dependent var S.D dependent var Akaike info criterion Schwarz criterion Hannan-Quinn criter Durbin-Watson stat Prob 0.0000 0.9949 0.9951 1.43E-05 0.009547 -7.127120 -7.018619 -7.085054 1.985704 Ph l c E: K t qu mơ hình SVAR ki nh ph hình K t qu mơ hình SVAR: Structural VAR Estimates Date: 10/06/14 Time: 19:09 Sample (adjusted): 58 Included observations: 54 after adjustments Estimation method: method of scoring (analytic derivatives) Convergence achieved after 18 iterations Structural VAR is over-identified (3 degrees of freedom) Model: Ae = Bu where E[uu']=I Restriction Type: short-run pattern matrix A= C(1) C(2) 0 0 B= C(4) 0 C(5) 0 C(6) 0 C(3) 0 0 C(7) Coefficient C(1) C(2) C(3) C(4) C(5) C(6) C(7) Std Error z-Statistic Prob 0.245124 -0.036794 -0.002240 0.005640 0.011271 0.017144 0.101685 0.068095 0.044769 0.007548 0.000543 0.001085 0.001650 0.009785 3.599722 -0.821869 -0.296821 10.39230 10.39230 10.39230 10.39230 0.0003 0.4112 0.7666 0.0000 0.0000 0.0000 0.0000 Log likelihood 558.3417 LR test for over-identification: Chi-square(3) 11.57886 Estimated A matrix: 1.000000 0.245124 Probability -0.036794 -0.002240 0.0090 a mô 0.000000 1.000000 0.000000 0.000000 0.000000 0.000000 Estimated B matrix: 0.005640 0.000000 0.000000 0.011271 0.000000 0.000000 0.000000 0.000000 K t qu ki 0.000000 1.000000 0.000000 0.000000 0.000000 1.000000 0.000000 0.000000 0.017144 0.000000 0.000000 0.000000 0.000000 0.101685 nh ph Null Hypothesis: RESID05 has a unit root Exogenous: Constant Lag Length: (Automatic - based on SIC, maxlag=10) t-Statistic Prob.* Augmented Dickey-Fuller test statistic -7.160177 0.0000 Test critical values: 1% level -3.560019 5% level -2.917650 10% level -2.596689 *MacKinnon (1996) one-sided p-values Augmented Dickey-Fuller Test Equation Dependent Variable: D(RESID05) Method: Least Squares Date: 12/29/14 Time: 20:37 Sample (adjusted): 58 Included observations: 53 after adjustments Variable Coefficient RESID05(-1) -0.998004 0.139383 -7.160177 0.0000 C -9.08E-05 0.000744 -0.122125 0.9033 0.501311 Mean dependent var -3.24E-05 R-squared Std Error t-Statistic Prob Adjusted R-squared S.D dependent var S.E of regression 0.005414 Akaike info criterion -7.562733 Sum squared resid 0.001495 Schwarz criterion Log likelihood 202.4124 Hannan-Quinn criter -7.534142 F-statistic 51.26814 Durbin-Watson stat Prob(F-statistic) 0.491533 0.007592 0.000000 -7.488383 1.962290 K t qu IRF t mơ hình SVAR: Response to Cholesky One S.D Innov ations Response of E to E Response of E to CLM S.E Response of E to CLY Response of E to CLR 008 008 008 008 004 004 004 004 000 000 000 000 -.004 -.004 -.004 -.004 -.008 -.008 10 -.008 Response of CLM to E 10 -.008 Response of CLM to CLM 10 Response of CLM to CLY 10 10 10 10 Response of CLM to CLR 04 04 04 04 02 02 02 02 00 00 00 00 -.02 -.02 -.02 -.02 -.04 -.04 10 -.04 Response of CLY to E 10 -.04 Response of CLY to CLM 10 Response of CLY to CLY Response of CLY to CLR 03 03 03 03 02 02 02 02 01 01 01 01 00 00 00 00 -.01 -.01 -.01 -.01 -.02 -.02 -.02 10 Response of CLR to E 10 -.02 Response of CLR to CLM 10 Response of CLR to CLY Response of CLR to CLR 2 2 1 1 0 0 -.1 -.1 -.1 -.1 -.2 -.2 10 -.2 10 -.2 10 K t qu ki nh ph Correlograms Autocorrelations with Std.Err Bounds Cor(E,E(-i)) Cor(E,CLM(-i)) Cor(E,CLY(-i)) Cor(E,CLR(-i)) 6 6 4 4 2 2 0 0 -.2 -.2 -.2 -.2 -.4 -.4 -.4 -.4 -.6 -.6 -.6 10 11 12 Cor(CLM,E(-i)) 10 11 12 -.6 Cor(CLM,CLM(-i)) 10 11 12 Cor(CLM,CLY(-i)) 10 11 12 Cor(CLM,CLR(-i)) 6 6 4 4 2 2 0 0 -.2 -.2 -.2 -.2 -.4 -.4 -.4 -.4 -.6 -.6 -.6 10 11 12 Cor(CLY,E(-i)) 10 11 12 -.6 Cor(CLY,CLM(-i)) 10 11 12 Cor(CLY,CLY(-i)) 10 11 12 Cor(CLY,CLR(-i)) 6 6 4 4 2 2 0 0 -.2 -.2 -.2 -.2 -.4 -.4 -.4 -.4 -.6 -.6 -.6 10 11 12 Cor(CLR,E(-i)) 10 11 12 -.6 Cor(CLR,CLM(-i)) 10 11 12 Cor(CLR,CLY(-i)) 10 11 12 Cor(CLR,CLR(-i)) 6 6 4 4 2 2 0 0 -.2 -.2 -.2 -.2 -.4 -.4 -.4 -.4 -.6 -.6 -.6 10 11 12 10 11 12 -.6 10 11 12 10 11 12 Residual Portmanteau Tests for Autocorrelations VAR Residual Portmanteau Tests for Autocorrelations Null Hypothesis: no residual autocorrelations up to lag h Date: 10/06/14 Time: 19:14 Sample: 58 Included observations: 54 Lags Q-Stat Prob Adj Q-Stat Prob df 10 11 12 27.65072 42.84343 56.68200 78.72192 110.6303 128.3655 138.9789 154.6607 175.7828 192.8161 210.1585 228.7563 NA* NA* NA* NA* 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 28.17244 43.94948 58.60208 82.40520 117.5696 137.5216 149.7158 168.1248 193.4713 214.3759 236.1546 260.0661 NA* NA* NA* NA* 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 0.0000 NA* NA* NA* NA* 16 32 48 64 80 96 112 128 *The test is valid only for lags larger than the VAR lag order df is degrees of freedom for (approximate) chi-square distribution Residual Serial Correlation LM Tests VAR Residual Serial Correlation LM Tests Null Hypothesis: no serial correlation at lag order h Date: 10/06/14 Time: 19:15 Sample: 58 Included observations: 54 Lags LM-Stat Prob 10 11 12 42.75903 25.13673 29.26977 22.27161 33.99861 18.68424 9.357370 15.25906 19.89954 16.41675 18.79972 22.65095 0.0003 0.0675 0.0222 0.1346 0.0054 0.2854 0.8980 0.5058 0.2248 0.4243 0.2792 0.1234 Probs from chi-square with 16 df Residual Normality Tests VAR Residual Normality Tests Orthogonalization: Cholesky (Lutkepohl) Null Hypothesis: residuals are multivariate normal Date: 10/06/14 Time: 19:16 Sample: 58 Included observations: 54 Component Skewness Chi-sq df Prob 1.784436 -0.011624 0.516049 0.256330 28.65791 0.001216 2.396759 0.591348 1 1 0.0000 0.9722 0.1216 0.4419 31.64724 0.0000 Joint Component Kurtosis Chi-sq df Prob 9.938395 3.799705 2.642841 2.596467 108.3180 1.438939 0.287015 0.366388 1 1 0.0000 0.2303 0.5921 0.5450 110.4103 0.0000 df Prob Joint Component Jarque-Bera 136.9759 1.440155 2.683774 0.957736 2 2 0.0000 0.4867 0.2614 0.6195 Joint 142.0576 0.0000 Residual Heteroskedasticity Tests: No Cross Terms VAR Residual Heteroskedasticity Tests: No Cross Terms (only levels and squares) Date: 10/06/14 Time: 19:17 Sample: 58 Included observations: 54 Joint test: Chi-sq df Prob 360.2853 320 0.0598 Individual components: Dependent R-squared F(32,21) Prob Chi-sq(32) Prob res1*res1 0.582243 0.914638 0.5990 31.44111 0.4947 res2*res2 0.590770 0.947370 0.5646 31.90156 0.4716 res3*res3 0.754914 2.021379 0.0474 40.76534 0.1377 res4*res4 0.779061 2.314028 0.0238 42.06930 0.1097 res2*res1 0.594471 0.962005 0.5495 32.10141 0.4617 res3*res1 0.807067 2.745183 0.0090 43.58160 0.0832 res3*res2 0.749068 1.958997 0.0550 40.44966 0.1452 res4*res1 0.667139 1.315293 0.2583 36.02550 0.2857 res4*res2 0.703148 1.554448 0.1464 37.96999 0.2158 res4*res3 0.759334 2.070561 0.0422 41.00405 0.1322 ... aM y* Q1 :1999 - Q2: 2013 IFS Lãi su t Fed fund rate i* Q1 :1999 - Q2: 2013 IFS Cung ti m* Q1 :1999 - Q2: 2013 IFS Khu v Q1 :1999 - Q2: 2013 c: e Q1 :1999 - Q2: 2013 IFS c y Q1 :1999 - Q2: 2013 ADB... 7/8/1998 25/02 /1999 (%) + /-7 26/02 /1999 01/7/2002 + /-0 ,1 01/7/2002 31/12/2006 + /-0 ,25 31/12/2006 24/12/2007 + /-0 ,5 24/12/2007 09/3/2008 + /-0 ,75 10/3/2008 26/6/2008 + /-1 27/6/2008 6/11/2008 + /-2 7/11/2008... giá USD /VND t ±2% lên m ch u c 16.977 VND/ 1USD, tích c c bán ngo i t có ch n l c nh m h tr kho n cho th ng Xu ng chung c n cu m a VND so v i giá th i cu liên t giá niêm y t t i NHTM bi n th giá