- #1
ad4stra
- 2
- 0
Hi everyone! I have (I think a major) problem so I'm hoping you could give me some useful advice.
I am working on my thesis where I am statistically estimating this type of equation:
dlny=α+β1*dlnx+β2*dlnz+β3*dlnx*dlnz
where dln stands for differencing a natural logarithm of the variable, eg
dlnz=ln(zt)-ln(zt-1)
so basically the approximation of the growth rate of x.
After I estimate this equation, I get certain values for α and for the βs and I have this nice equation.
My research question is:
What will be the marginal effect of an increase in dlnx on dlny if z doesn't exist (ie it is zero).
Obviously, the derivative of dlny with respect to dlnx is
∂lny/∂lnx=β1+β3*dlnz
and now I need to calculate how much that is when z (not dlnz) doesn't exist.
Obviously, I have problem since dlnz in this case isn't defined:
dlnz=ln(0)-ln(0)
Is there any way I can manipulate mathematically my problem in order to get an answer to my question??
Thank you very much in advance!
I am working on my thesis where I am statistically estimating this type of equation:
dlny=α+β1*dlnx+β2*dlnz+β3*dlnx*dlnz
where dln stands for differencing a natural logarithm of the variable, eg
dlnz=ln(zt)-ln(zt-1)
so basically the approximation of the growth rate of x.
After I estimate this equation, I get certain values for α and for the βs and I have this nice equation.
My research question is:
What will be the marginal effect of an increase in dlnx on dlny if z doesn't exist (ie it is zero).
Obviously, the derivative of dlny with respect to dlnx is
∂lny/∂lnx=β1+β3*dlnz
and now I need to calculate how much that is when z (not dlnz) doesn't exist.
Obviously, I have problem since dlnz in this case isn't defined:
dlnz=ln(0)-ln(0)
Is there any way I can manipulate mathematically my problem in order to get an answer to my question??
Thank you very much in advance!