Dear All,
I'd like to estimate the variance of a variable
derived from an OLS result (estimates) using
bootstrap.
Suppose that I have a regression equation
y = a + bx + cz + error
Then let y_hat be the predicted value.
What I'd like to compute is a variance for
a + z*y_hat
So what I did is to run
bs "regress y x z" (_b[cons] +
z*(_b[cons]+_b[x]*x+_b[z]*z)), reps(100)
Does this syntax make sense?
Or perhaps there's another way to write it more
shortly by using the "predict" command after regress?
Sincerely
Sjamsu
__________________________________
Do you Yahoo!?
New and Improved Yahoo! Mail - 100MB free storage!
http://promotions.yahoo.com/new_mail
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
