Hi,
I am doing a simple linear regression where the dependent variable is venture capital returns (multiple of invested capital) and the independent is the country of the target company. The independent variable is a dummy (1= China, 0 = USA)..
I only want to determine if the return is affected by the country but there are other variables i would like to control for.
This includes sector, size of investment and more.
Where can i find theoretical literature on this subject? I am not sure what it is called - is it Cofounding variables?
Regards
Hi Dennis,
I think one interesting initial approach of regression with dummy variables is the following book. http://methods.sagepub.com/book/regression-with-dummy-variables
It will help you to understand them and to develop your models.
Dummy variables work best when there are clear and observable deterministic shifts in an endogenous, stochastic or random variable.
As the name suggests, such variables do not vary much.
Dummy variables should not be used as a substitute for a more careful explanation of the underlying stochastic relationships that might exist.
- Badges
- Science topic