Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: question on bootrapping in stata


From   Lijiang Shen <lshen@uga.edu>
To   statalist@hsphsun2.harvard.edu
Subject   st: question on bootrapping in stata
Date   Fri, 14 Sep 2007 19:18:37 -0400

Dear All,

I have a question regarding bootstrapping in Stata. In a paper, I simulated a bivariate data set and then censored one variable, thus creating a censored DV. I ran a tobit regression model, and then bootstrapped the model to repeat 1000 times, which yielded estimates of standard errors and 95% confidence intervals for the tobit coefficient. One reviewer commented that nothing could be gained from bootstrapping the tobit model since there is one sample. My understanding was bootstrapping did provide some estimate of the sampling distribution of tobit coefficients and can be used to assess their robustness. But I could be totally wrong since I have very limited knowledge on monte carlo study and bootstrapping. I wonder if you could provide some comments/suggestions/advice?

Thank you very much.

Lijiang
*
* 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/




© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index