Statalist


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

R: st: RE: montecarlo simulations with actual distributions


From   "Carlo Lazzaro" <carlo.lazzaro@tin.it>
To   <statalist@hsphsun2.harvard.edu>
Subject   R: st: RE: montecarlo simulations with actual distributions
Date   Wed, 2 Jul 2008 14:16:26 +0200

Dear Emanuele,
following Martin'reply and Maarten's advice on performing bootstrap:
-the number of replications may vary according what you are intended to
check for (plase, see Efron B, Tibshirani RJ. An Introduction to the
Bootstrap. Chapman and Hall: New York, 1993);
- for instance, as far as the comparison of the mean of costs in health care
programmes evaluation is concerned, the number of bootstrap replications
vary between 1000 and (more often) 10,000. For confidence interval and
regression coefficients the number is usually lower (again, please see the
abovementioned reference).

If you make up your mind to perform a bootstrap test on your original data
set, another decision to be taken is what kind of bootstrap: parametric or
non parametric? I would recommend the non parametric bootstrap, since it is
teheoretically closer to the core mininig ot this procedure (ie no
assumptions about the distribution from which the original sample has been
drawn) and requires less computational effort. Usually, parametric and non
parametric bootstrap tests give back similar results.

HTH and Kind Regards,

Carlo

-----Messaggio originale-----
Da: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di emanuele
canegrati
Inviato: mercoledý 2 luglio 2008 13.51
A: statalist@hsphsun2.harvard.edu
Oggetto: RE: st: RE: montecarlo simulations with actual distributions


Martin,





thank you very much indeed. Is there any minimum number of simulations to
have reliable results?





Best





Emanuele


> From: martin.weiss@uni-tuebingen.de
> To: statalist@hsphsun2.harvard.edu
> Subject: st: RE: montecarlo simulations with actual distributions
> Date: Wed, 2 Jul 2008 12:36:15 +0200
>
> - h simulate - is for you. Its example program syntax at the bottom gives
> you the clearest possible advice as to the implementation of MC in Stata.
>
> Martin Weiss
> _________________________________________________________________
>
> Diplom-Kaufmann Martin Weiss
> Mohlstrasse 36
> Room 415
> 72074 Tuebingen
> Germany
>
> Fon: 0049-7071-2978184
>
> Home: http://www.wiwi.uni-tuebingen.de/cms/index.php?id=1130
>
> Publications: http://www.wiwi.uni-tuebingen.de/cms/index.php?id=1131
>
> SSRN: http://papers.ssrn.com/sol3/cf_dev/AbsByAuth.cfm?per_id=669945
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of emanuele
> canegrati
> Sent: Wednesday, July 02, 2008 12:30 PM
> To: statalist@hsphsun2.harvard.edu
> Subject: st: montecarlo simulations with actual distributions
>
>
> Dear Users,
>
>
>
>
>
> I have to perform some montecarlo simulations of market returns with
STATA.
> I would like to generate these returns from the original time series under
> the condition they reflect the actual PDF and so I think I need to
calculate
> the mean and the standard deviations of returns. Which is the programme I
> have to write? I have to perform any non-parametric analysis before in
order
> to calculate the actual distribution of my returns?
>
>
>
>
>
> Thank you in advance.
>
>
>
>
>
> Kind Regards,
>
>
>
>
>
> Emanuele Canegrati
>
> _________________________________________________________________
> News, entertainment and everything you care about at Live.com. Get it now!
> http://www.live.com/getstarted.aspx
> *
> * 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/
>
> *
> * 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/

_________________________________________________________________
Invite your mail contacts to join your friends list with Windows Live
Spaces. It's easy!
http://spaces.live.com/spacesapi.aspx?wx_action=create&wx_url=/friends.aspx&;
mkt=en-us
*
*   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/



*
*   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