VECM. Model Two. Part 4 of 4.VECM

[@sayedhossain23]

Both test are equally valuable so you can take result of any one by taking one as benchmark. Best would be if both tell the same decision.

[@samermehibel1324]

I have noticed that for 5 cointegrating relatiohships the statitic is significant as you can see below No. of CE(s) Eigenvalue Statistic Critical Value Prob.** At most 5 0.073780 3.065756 3.841466 0.0800 This means that we have 6 cointegrating relationships which is equal to the number of variables that we have for this study and in this car when the number of cointegration relationships is equal to the number of variables we should apply VAR model, what do you think?

[@samermehibel1324]

You notice sir that for 1 and 2 the p value is significant and after that 3 and 4 is not significant and then 5 cointegrating relationships are significant. which means that we have 6 cointegration relationships which is the same as the number of variables we have so VAR model can be applied.

[@sayedhossain23]

Indeed there are five cointegration equations not 6. So variables are cointegtated. So You can run VECM now, not VAR,

[@samermehibel1324]

1-According to the results of johansen test i found trace test indated the existence of 2 cointegrating relationships but the max egenvalues test indicated 0 coitegrating relationships. Which test to believe?

[@abimelechpayegbatu5926]

Hello sir, your videos are good in showing the direction of causality. Could you upload videos on how to calculate the exact short-run and long-run coefficients? This is important because determining the direction of causality is not an issue, but knowing how the independent variables influence the dependent variable is import. The is very import if you could do it for Eviews 9.

[@sayedhossain23]

Thank you. I would like to invite you to join Hossain Academy Facebook at below link and post your question there for feedback. Thank you, Sayed Hossain from Hossain Academy facebook.com/groups/hossainacademy/