How to Interpret Cointegration Results? A Stata and Eviews Example

How to Interpret Cointegration Results?

In this simple tutorial with estimation examples of cointegration in Stata and Eviews and Interpretation is provided. This guide is for beginners in Time Series Analysis.  The tutorial is written for those learners of cointegration analysis who wish to follow step by step and get the results for the test of cointegration and then need to interpret the results.

Estimate and Interpret Cointegration Results?

In this guide, we use Stata and Eviews for estimation of Cointegration following few techniques commonly found in literature and books of Econometrics. The first section of this tutorial will sum up the steps in Stata and Eviews for testing cointegration using Johansen-Jusuleus Approach and Engle Granger Approach.

How to test cointegration using Eviews?

To test for cointegration using Johansen Approach using Eviews, please follow these steps:

For Engle Granger Cointegration test, follow these steps:

The Engle Granger Cointegration test is based on single equation system. We have to estimate an OLS regression model with DV and IVs and predict the residuals. Then an ADF on the residuals series can be run to test the hypothesis of unit root of residuals series. If we reject the null hypothesis of unit root of residuals, the residuals will be stationary which shows no cointegration.

How to test cointegration using Stata?

In the following, we will outline the steps

The Johansen cointegration test in Stata can be computed using the following process:

egranger is the Stata command that conducts tests for cointegration proposed by Engle and Granger (1987), reporting test statistics plus critical values calculated by MacKinnon (1990, 2010). egranger will also estimate an ECM (Error Correction Mechanism) model using the 2-step procedure proposed by Engle and Granger (1987).

Example of codes using egranger are following:

egranger ln_ne ln_se

egranger ln_ne ln_se, lags(2)

egranger ln_ne ln_se, lags(2) trend

egranger ln_ne ln_se ln_me, lags(1) qtrend

How to interpret test of cointegration?

We need to know the hypothesis of each test of cointegration to interpret the test. Using the conventional approach a p-value of the test less than 0.05 will indicate significance. So let us note the null hypothesis of both tests of cointegration including Johansen approach and Engle Granger One Equation Approach of Cointegration.


We hope this detailed tutorial will help us learn how to Interpret Cointegration Results. In summary, we can see that all results can be easily interpreted when the null hypothesis and distribution of the test statistic is understood. Like the Engle Granger hypothesis follows simply the unit root of residuals from step 1 regression and can be interpreted based on the same that if the residuals are found unit root then it would indicate the series in step 1 regression will follow cointegration.

Tags: , , ,

Professionally trained and highly recognized online course provider in Advanced Econometrics and Top Freelancer in Stata, Eviews, SPSS, Nvivo10/11, WinRATS, GAUSS, Gretl and Minitab. Anees has helped 1100+ clients (organizations, students and researchers) from around the world in applied econometrics and applied statistics. He has completed research and analytics in corporate governance, financial performance, economics problems, business evaluation, value at risk, options pricing, stock evaluation, currency and pairs trading and backtesting using major statistical softwares. Academically, he has masters in Econometrics and Economics from The University of Sheffield, UK.


Read More Post