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]

Re: st: BC confidence interval


From   Stas Kolenikov <skolenik@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: BC confidence interval
Date   Wed, 15 Dec 2010 17:46:14 -0500

Something is VERY wrong with your bootstrap. The fact that your bias
is 20 times greater than your standard error is troublesome, to say
the least.

We could probably say more about your problem if you provided the
complete syntax and output, but since -cluster()- option is mentioned,
I suspect that Stata does not compute the necessary acceleration
coefficients that are based on the jackknife pass through the data
before the bootstrap. In turn, the jackknife is not making sense since
the data are not i.i.d.

On Wed, Dec 15, 2010 at 5:24 PM, Xu, Haiyong <HXu@mednet.ucla.edu> wrote:
> I was using bootstrap to get the confidence interval. Stata gave me the normal-based and percentile-based CI, but bias-corrected CI is missing. Does someone know how to get the bc CI? Here is the output. Thanks.
>                          (Replications based on 13428 clusters in cluster_id)
> ------------------------------------------------------------------------------
>             |    Observed               Bootstrap
>             |       Coef.       Bias    Std. Err.  [95% Conf. Interval]
> -------------+----------------------------------------------------------------
>       p2005 |   102.91307  -29.08997    1.582254    99.81191   106.0142   (N)
>             |                                       71.44293   76.52544   (P)
>             |                                              .          .  (BC)
>       p2006 |   95.265941   27.46531   2.5908633    90.18794   100.3439   (N)
>             |                                       117.8621   125.2468   (P)
>             |                                              .          .  (BC)
>       p2007 |   101.33245   17.45957   4.4932015    92.52593    110.139   (N)
>             |                                        112.169    126.074   (P)
>             |                                              .          .  (BC)
>     d_06_05 |  -7.6471301   56.55528    2.275321   -12.10668  -3.187583   (N)
>             |                                       44.79739   51.67213   (P)
>             |                                              .          .  (BC)
>     d_07_05 |   -1.580624   46.54955   3.9348652   -9.292818    6.13157   (N)
>             |                                       39.12644   50.84778   (P)
>             |                                              .          .  (BC)
> ------------------------------------------------------------------------------
> (N)    normal confidence interval
> (P)    percentile confidence interval
> (BC)   bias-corrected confidence interval
>
> Haiyong
>
> IMPORTANT WARNING:  This email (and any attachments) is only intended for the use of the person or entity to which it is addressed, and may contain information that is privileged and confidential.  You, the recipient, are obligated to maintain it in a safe, secure and confidential manner.  Unauthorized redisclosure or failure to maintain confidentiality may subject you to federal and state penalties. If you are not the intended recipient, please immediately notify us by return email, and delete this message from your computer.
>
> *
> *   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/
>



-- 
Stas Kolenikov, also found at http://stas.kolenikov.name
Small print: I use this email account for mailing lists only.

*
*   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