协整检验全是拒绝原假设，怎么办呢？

4586

收藏 2016-03-15

单位根检验之后是不平稳，接着一阶差分检验，是平稳的。
VAR模型构建之后，显示最优滞后期是3，于是确定协整检验的最大滞后期为2.
但是，做出来协整检验的结果却如下所示。
根据迹统计量检验结果得出全部拒绝原假设，怎么办好呢？是哪一步出了问题吗？谢谢！！！
Date: 03/15/16 Time: 22:07
Sample (adjusted): 1997 2013
Included observations: 17 after adjustments
Trend assumption: Linear deterministic trend
Series: LNY LNL LNG LNMM
Lags interval (in first differences): 1 to 2

Unrestricted Cointegration Rank Test (Trace)

Hypothesized Trace 0.05
No. of CE(s) Eigenvalue Statistic Critical Value Prob.**

None *          0.941629    102.8585    47.85613    0.0000
At most 1 *    0.850144    54.56246    29.79707    0.0000
At most 2 *    0.596397    22.29511    15.49471    0.0040
At most 3 *    0.332458    6.870611    3.841466    0.0088

Trace test indicates 4 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 Max-Eigen 0.05
No. of CE(s) Eigenvalue Statistic Critical Value Prob.**

None *          0.941629    48.29603    27.58434    0.0000
At most 1 *    0.850144    32.26735    21.13162    0.0009
At most 2 *    0.596397    15.42450    14.26460    0.0326
At most 3 *    0.332458    6.870611    3.841466    0.0088

Max-eigenvalue test indicates 4 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):

LNY LNL LNG LNMM
0.034314    7.232485    5.090380 -0.035877
-63.35064 -42.78012    59.48214    4.224367
1.021463    1.699730    10.96539    2.508587
-23.68231 -9.722196    27.31180    3.292039

Unrestricted Adjustment Coefficients (alpha):

D(LNY) -0.026989    0.022133    0.015984 -0.025338
D(LNL) -0.016696    0.008980    0.005692    0.015104
D(LNG)    0.006994 -0.007434    0.029240    0.018403
D(LNMM)    0.737682    0.120677    0.192326 -0.279425

1 Cointegrating Equation(s): Log likelihood    98.99484

Normalized cointegrating coefficients (standard error in parentheses)
LNY LNL LNG LNMM
1.000000    210.7739    148.3472 -1.045538
   (25.6639)    (37.9661)    (8.34525)

Adjustment coefficients (standard error in parentheses)
D(LNY) -0.000926
   (0.00071)
D(LNL) -0.000573
   (0.00038)
D(LNG)    0.000240
   (0.00065)
D(LNMM)    0.025313
   (0.00765)

2 Cointegrating Equation(s): Log likelihood    115.1285

Normalized cointegrating coefficients (standard error in parentheses)
LNY LNL LNG LNMM
1.000000    0.000000 -1.418765 -0.063536
   (0.10181)    (0.02535)
0.000000    1.000000    0.710553 -0.004659
   (0.14498)    (0.03610)

Adjustment coefficients (standard error in parentheses)
D(LNY) -1.403062 -1.142045
   (1.19504)    (0.81845)
D(LNL) -0.569462 -0.504918
   (0.66531)    (0.45565)
D(LNG)    0.471188    0.368609
   (1.18880)    (0.81418)
D(LNMM) -7.619624    0.172717
   (13.8209)    (9.46558)

3 Cointegrating Equation(s): Log likelihood    122.8408

Normalized cointegrating coefficients (standard error in parentheses)
LNY LNL LNG LNMM
1.000000    0.000000    0.000000    0.263265
   (0.04749)
0.000000    1.000000    0.000000 -0.168329
   (0.02808)
0.000000    0.000000    1.000000    0.230342
   (0.03233)

Adjustment coefficients (standard error in parentheses)
D(LNY) -1.386735 -1.114877    1.354402
   (1.13225)    (0.77594)    (1.08470)
D(LNL) -0.563648 -0.495243    0.511580
   (0.65128)    (0.44633)    (0.62393)
D(LNG)    0.501055    0.418309 -0.085963
   (0.96089)    (0.65851)    (0.92054)
D(LNMM) -7.423170    0.499620    13.04212
   (13.0328)    (8.93153)    (12.4855)