Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, is already up and running.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: st: bootstrap multiple equations?

From   "Tiago V. Pereira" <>
Subject   RE: st: bootstrap multiple equations?
Date   Wed, 18 Aug 2010 18:44:35 -0300 (BRT)

Austin, if you don't want to compare the different models, the most
straightforward way is to create a r(class) program that outputs directly
the coefficients.

Within the program, you can write the N different models as locals, and
loop over all possible models, outputting the results as a a scalar.

Say your program loops over 10 models and outputs  r(coef_1) ... r(coef_10).

You can create a single local

forvalues i = 1/10 {

		local coefs " `coefs' r(coef_`i')"


dis "`coefs'"

and ask for the -bootstrap- to pick up all the returned coefficients with
this single local. Example:

 bootstrap `coefs', reps(1000) : yourpogram

Hope this helps.


*   For searches and help try:

© Copyright 1996–2016 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index