# st: bootstrapping

 From "Vincenzo Carrieri" To statalist@hsphsun2.harvard.edu Subject st: bootstrapping Date Thu, 10 Jul 2008 20:23:15 +0200

```Dear statalister,
I have the following stata output:

> esenti = 0

Variable |       Obs        Mean    Std. Dev.       Min        Max
______________________________________________________
nnotti |      1032    4.545543    4.936243          1         80

-> esenti = 1

Variable |       Obs        Mean    Std. Dev.       Min        Max
__________________________________________________________
nnotti |      3125     9.78528    12.73163          1         90

"Esenti" is a dummy variable that indicates if a person copayment free
or not. "nnotti" are the numbers of days spent in a hospital.
So, the total number of nights, are 1032 (Obs)  x 4.545543 + 3125 X
9.78528 = 35270
I wish to calculate the proportion of nights spent by esenti=1 out of
total nights. I compute simply this proportion, but It's just a sample
proportion. Is it meaningful to randomly replicate my sample 1000
times and compute my proportion for each of these samples? It allows
me to have a range of values of my proportion and not only a single
sample value. I think this should be bootstrapping, but I don't have a
deep knowledge about this argument. If yes, how to do it on stata?

I appreciate any advice or comment.
Many thanks,

Vincenzo
*
*   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/
```