Monte Carlo
Related Products:
Monte Carlo test: Is it necessary to introduce an error term randomly generated?
I'm making a Monte Carlo experiment that examines alternative methods of OLS modeling constructs a dependent variable. Is it necessary for me to generate artificially error "expression" for my dependent variable constructed?
It depends on the details of what you want to model, but generally you want to add an error term realistic. See here for examples: http://shazam.econ.ubc.ca/intro/index.html
