GMM Estimation

[ftimsah]

Hi everyone,

I am very new to Eviews and I am trying to estimate a New Keynesian Phillips Curve. But, I face problems with estimating the parameter equation, which is the following:

(c(1)+c(2)*(1-c(1)*(1-c(3))))*gdp_def-(1-c(1))*(1-c(2))*(1-c(1)*c(3))*labinc_gdp-c(1)*c(3)*gdp_def(+1)=0

the IV list is:

tefe(-1) tefe(-2) tefe(-3) tefe(-4) tufe(-1) tufe(-2) tufe(-3) tufe(-4) reel(-1) reel(-2) reel(-3) reel(-4) gdp_def(-2) gdp_def(-3) gdp_def(-4) exc(-1) exc(-2) exc(-3) exc(-4)

every time I run the regression, the "near singular matrix" warning is coming on the screen which is very annoying.

I made a search under other topics and found a user who faced a similar situation. But, there was no rational explanation for this warning. Why is eviews not running the regression? What does "near singular matrix" mean in this situation? If someone can help me out with this, I would be very grateful.

Thanks in advance.

[EViews Gareth]

I made a search under other topics and found a user who faced a similar situation. But, there was no rational explanation for this warning. Why is eviews not running the regression? What does "near singular matrix" mean in this situation? If someone can help me out with this, I would be very grateful.

Thanks in advance.

Actually the rational explanation is that EViews encountered a singular matrix problem during estimation. It then reported to you that it had encountered a singular matrix.

Obviously the reason EViews is not running the regression is because it encountered a singular matrix.


The most likely cause is that your regressors or your instruments are co-linear.

[kokshenur]

Try larger samples.