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, statalist.org is already up and running.


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

st: bootstrap validation and c statistics (help me please !)


From   "Hong, Sounman" <sounman_hong@hksphd.harvard.edu>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   st: bootstrap validation and c statistics (help me please !)
Date   Tue, 24 May 2011 18:38:08 -0400

I need to validate my model. I heard that I need to do either by a cross-validation or a bootstrap. I have three questions.

1. What is the best statistics to report if I want to show that my model is validated using bootstrap? I read a paper that reported C statistics, although I have to study what that is. Do you recommend me reporting C statistics?

2. Does STATA have a code that generates a shrinkage factor? 

3. I wrote below my STATA code that performs bootstrap and get a C statistics. But I got an error and I don't know why. Please advise.

use bootstrap.dta, clear
logit DEPVAR BPA
estat concordance
matrix b = e(b)
capture program drop mysim
program define mysim, rclass
    use bootstrap.dta, clear
    bsample
    lroc BPA, nograph beta(b)
    return scalar c=r(c)
end
simulate c=r(c), reps(100): mysim


Thank you in advance. Any advice would be greatly appreciated.
-Sounman
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   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   |   Site index