Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

# RE: st: Solution for Autocorrelation in Lag orders for VAR

 From Muhammad Akram To Subject RE: st: Solution for Autocorrelation in Lag orders for VAR Date Mon, 6 Feb 2012 00:07:44 +0500

```Dear,

Thanks again. I have tested the variables for stationary and cointegration. They are stationary at first differance but have unit root at levels. So in my VAR model I am using them in difference. I tried VECM but it fails to include one trend variable (technological growth) which covers affectiveness of labour. If I use 3lags and Var at difference all is fine for other two countries but for one country only LM test fails at 1st lag it works on other two lags. What would you suggest in this case? Any reference which I can use to deal with bit of autocorelation.

Thanks again

aasim

---------------------------------------- > From: kit.baum@bc.edu > To: statalist@hsphsun2.harvard.edu > Date: Sun, 5 Feb 2012 12:05:21 -0500 > Subject: re:RE: st: Solution for Autocorrelation in Lag orders for VAR > > <> > Also it gives problem for eigen values table and graph with few values outside eigen circle.So I have to stick to this lag length. Do you have any idea to solve this issue in STATA. > > In Stata (not STATA!) this evidence from the eigensystem suggests that some of your variables fail to satisfy the requirements for dynamic stability of the VAR, possibly because they are unit root (I(1)) processes. It is difficult to test them for stationarity given only 30 obs. but if other research using these variables has focused on their differences rather than their levels, I would heed it. > > Kit > > > Kit Baum | Boston College Economics & DIW Berlin | http://ideas.repec.org/e/pba1.html > An Introduction to Stata Programming | http://www.stata-press.com/books/isp.ht!
ml > An Introduction to Modern Econometrics Using Stata | http://www.stata-press.com/books/imeus.html > > > * > * For searches and help try: > * http://www.stata.com/help.cgi?search > * http://www.stata.com/support/statalist/faq > * http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
```