我做的是99年到08年北京市批发零售销售总额的时间序列平稳性检验。结果如下(只有intercept):
ADF Test Statistic -1.442021 1% Critical Value* -5.2459
5% Critical Value -3.5507
10% Critical Value -2.9312
*MacKinnon critical values for rejection of hypothesis of a unit root.
Augmented Dickey-Fuller Test Equation
Dependent Variable: D(WRT,3)
Method: Least Squares
Date: 05/18/10 Time: 22:53
Sample(adjusted): 2003 2008
Included observations: 6 after adjusting endpoints
Variable Coefficient Std. Error t-Statistic Prob.
D(WRT(-1),2) -1.884895 1.307120 -1.442021 0.2450
D(WRT(-1),3) 0.215131 0.733248 0.293394 0.7883
C 1681.838 1607.749 1.046082 0.3724
R-squared 0.688109 Mean dependent var 756.8506
Adjusted R-squared 0.480182 S.D. dependent var 5152.666
S.E. of regression 3714.990 Akaike info criterion 19.58499
Sum squared resid 41403455 Schwarz criterion 19.48087
Log likelihood -55.75498 F-statistic 3.309376
Durbin-Watson stat 1.904503 Prob(F-statistic) 0.174182
请高手帮我详细的讲一下好吗?我没学过计量学,是毕业设计里面临时要用的,看了好几天的书感觉还是不太明白,请高手解释一下为什么平稳或者不平稳,不要只简单说结论,比如adf与1、5、10%的对比怎么比的从而得出结论,还有p值和t值分别有啥意义?非常感谢!!!