ADF Unit Root Tests

[cal.j.heseltine]

Hi,

I have just tried to run some unit root tests, I have ran them for intercept, trend and Intercept and none. The first two results were ok suggesting the data was stationary but my third output confused me;

Null Hypothesis: XCH has a unit root
Exogenous: None
Lag Length: 1 (Automatic - based on SIC, maxlag=21)

t-Statistic Prob.*

Augmented Dickey-Fuller test statistic 2.125776 0.9922
Test critical values: 1% level -2.574320
5% level -1.942110
10% level -1.615846

*MacKinnon (1996) one-sided p-values.


Augmented Dickey-Fuller Test Equation
Dependent Variable: D(XCH)
Method: Least Squares
Date: 03/14/15 Time: 11:55
Sample (adjusted): 1994M03 2014M10
Included observations: 248 after adjustments

Variable Coefficient Std. Error t-Statistic Prob.

XCH(-1) 0.001397 0.000657 2.125776 0.0345
D(XCH(-1)) 0.343256 0.059927 5.727948 0.0000

R-squared 0.094039 Mean dependent var 0.243508
Adjusted R-squared 0.090356 S.D. dependent var 0.924281
S.E. of regression 0.881535 Akaike info criterion 2.593729
Sum squared resid 191.1678 Schwarz criterion 2.622063
Log likelihood -319.6224 Hannan-Quinn criter. 2.605135
Durbin-Watson stat 1.941209

It produced a positive tau-value but the significance levels are negative, how do I interpret this?