Cointegrating Equations

[olubbock]

Hi,

I am studying the determinants of China's Trade Growth since 1982 using a VECM model. The variables used are: TRADE, FDI, Exchange rates, Wages, Tariffs, World Income

My query relates to the specification and interpretation of the VECM. My Johansen/Engle-Granger cointegration tests came up with mixed results as to how many cointegrating relationships exist in the model but I have chosen to use 2 cointegrating equations in my VECM specification.

With my VECM results, how do I interpret the coefficients for each cointegrating equation? I know that the first one measures "the speed of adjustment towards equilibrium", but what about the second one?

The coefficients and probability values for each are:
CE1: -0.409, 0.0048 (ie significant)
CE2: 0.067, 0.229 (ie not significant)

If it is any help, in the "endogenous variables" box, I listed the my variables in the order: Ln(Trade), Ln(FDI), Ln(EX), Ln(WorldY), Ln(Wages), Ln(Tariffs)

Any help would be much appreciated. Thanks

[jjcale5]

Hello,

I am studying on an article about environmental kuznets curve.

The model is logco2 = logGDP + logGDP^2 + logGDP^3
The man who prepared the paper had found the variables in his cointegration analysis like
-3.96 for logGDP(-1) 1.20 for logGDP^2(-1) and -0.09 for loggdp^3

and at last, he wrote his model like ;

logco2 = 3.96logGDP - 1.20logGDP^2 + 0.0923logGDP^3

is it normal ?
if it is the case, why ?

thanks very much