本人想请教下ADF检验应该是双侧检验还是单侧的?eviews和r软件做出的结果给出的p值不同,貌似eviews用的的单侧检验,r则是双侧的!应该怎么判断啊?eviews结果: t-Statistic Prob.*
Augmented Dickey-Fuller test statistic 5.938425 1.0000
Test critical values: 1% level -2.584539
5% level -1.943540
10% level -1.614941
*MacKinnon (1996) one-sided p-values.
r软件的输出结果:
###############################################
# Augmented Dickey-Fuller Test Unit Root Test #
###############################################
Test regression none
Call:
lm(formula = z.diff ~ z.lag.1 - 1 + z.diff.lag)
Residuals:
Min 1Q Median 3Q Max
-24.3251 -1.3258 -0.1377 2.7119 20.7128
Coefficients:
Estimate Std. Error t value Pr(>|t|)
z.lag.1 0.09498 0.01610 5.900 4.50e-08 ***
z.diff.lag1 -0.78677 0.10462 -7.520 1.93e-11 ***
z.diff.lag2 -0.66404 0.12011 -5.529 2.37e-07 ***
z.diff.lag3 -0.56064 0.11917 -4.705 7.78e-06 ***
z.diff.lag4 -0.66707 0.11218 -5.946 3.64e-08 ***
z.diff.lag5 -0.74458 0.11615 -6.411 4.21e-09 ***
z.diff.lag6 -0.58711 0.12428 -4.724 7.19e-06 ***
z.diff.lag7 -0.69566 0.11622 -5.986 3.04e-08 ***
z.diff.lag8 -0.57383 0.12070 -4.754 6.37e-06 ***
z.diff.lag9 -0.70562 0.11207 -6.296 7.22e-09 ***
z.diff.lag10 -0.62596 0.11992 -5.220 9.09e-07 ***
z.diff.lag11 -0.58618 0.11574 -5.065 1.76e-06 ***
z.diff.lag12 0.49678 0.10989 4.521 1.62e-05 ***
---
Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1
Residual standard error: 5.044 on 105 degrees of freedom
Multiple R-squared: 0.8688, Adjusted R-squared: 0.8526
F-statistic: 53.5 on 13 and 105 DF, p-value: < 2.2e-16
Value of test-statistic is: 5.8995
Critical values for test statistics:
1pct 5pct 10pct
tau1 -2.58 -1.95 -1.62