# How to read UNIT ROOT TEST results obtained from EVIEWS? I mean what values do we study to interpret our result?

Null Hypothesis: D(OIL_PRICES) has a unit root


Exogenous: Constant
Lag Length: 0 (Automatic - based on SIC, maxlag=22)

        t-Statistic   Prob.*


Augmented Dickey-Fuller test statistic -37.22113 0.0000 Test critical values: 1% level -3.435299
5% level -2.863613
10% level -2.567923

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

Augmented Dickey-Fuller Test Equation
Dependent Variable: D(OIL_PRICES,2) Method: Least Squares
Date: 11/29/14 Time: 18:57

Variable Coefficient Std. Error t-Statistic Prob.

D(OIL_PRICES(-1)) -1.042433 0.028006 -37.22113 0.0000 C 0.050065 0.043335 1.155289 0.2482

R-squared 0.522716 Mean dependent var -0.003875 Adjusted R-squared 0.522339 S.D. dependent var 2.230622 S.E. of regression 1.541651 Akaike info criterion 3.705162 Sum squared resid 3006.510 Schwarz criterion 3.713283 Log likelihood -2345.220 Hannan-Quinn criter. 3.708213 F-statistic 1385.413 Durbin-Watson stat 2.002267 Prob(F-statistic) 0.000000

• I think I don't see some hypothesis testing in your result. There are some tests like the Dickey Fuller or KPSS test but you didn't give the results here. You probably have to state some where in EViews that you want to conduct such a test. Take a look at this youtube video. He explains how to do everything: youtube.com/watch?v=-ePFfyGxz4I – random_guy Nov 29 '14 at 14:13
• Could you replace your written text by posting simply a screen shot of your outputP This will be highly beneficial for others who have the same question and possibly come to this page. – random_guy Dec 3 '14 at 17:27
• Sir can you help me with guiding how to vote for your answer? – Faiza Sajjad Dec 19 '14 at 4:55
• Hi Faiza, thank you for accepting my answer. However, for voting one needs at least 15 points and you have only 13 so far. I already up voted your question. So, I think I cannot do more. But maybe in the future when you have two points more you remember me and come back here to up vote. :) But you can also go to some questions or answers of other users and just edit them. I think an accepted edit gives 2 points. ;) Or you can just ask another good question and somebody will up vote you there. This gives 5 points. – random_guy Dec 19 '14 at 10:05

You conducted a Augmented Dickey Fuller test. The hypothesis of this test are $H_0$: "Process has unit root" vs. $H_1$: "Process has no unit root". The test statistic is $-37.22113$. Now you need to compare this with the critical values under $H_0$. The critical values are given with:
$1\%: -3.435299 \\ 5\%: -2.863613 \\ 10\%: -2.567923.$
Since your test statistic is much lower than all of the critical values you can reject $H_0$ at a significance level $\ \ <1\%$. So you can conclude with a very low probability of making an error that your time series has no unit root. So, you can reject $H_0$.