Wild bootstrap

classic Classic list List threaded Threaded
7 messages Options
Reply | Threaded
Open this post in threaded view
|

Wild bootstrap

Paulo Grahl
Dear list members,

I am wondering whether it is possible to use 'boot' package (or any
other) in order to use the wild bootstrap method.
Any help, examples, would be appreciated.
Thanks,
Paulo

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.
Reply | Threaded
Open this post in threaded view
|

Re: Wild bootstrap

Chiquoine, Ben
I was doing some bootstrapping with R a while back and found the
following document helpful. Maybe you will as well.
http://www.statoo.com/en/publications/bootstrap_scgn_v131.pdf

Ben

-----Original Message-----
From: [hidden email]
[mailto:[hidden email]] On Behalf Of Paulo
Grahl
Sent: Monday, March 29, 2010 5:00 PM
To: [hidden email]
Subject: [R-SIG-Finance] Wild bootstrap

Dear list members,

I am wondering whether it is possible to use 'boot' package (or any
other) in order to use the wild bootstrap method.
Any help, examples, would be appreciated.
Thanks,
Paulo

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions
should go.
___________________________________________
This message and any attached documents contain
information which may be confidential, subject to
privilege or exempt from disclosure under applicable
law. These materials are solely for the use of the
intended recipient. If you are not the intended
recipient of this transmission, you are hereby
notified that any distribution, disclosure, printing,
copying, storage, modification or the taking of any
action in reliance upon this transmission is strictly
prohibited. Delivery of this message to any person
other than the intended recipient shall not
compromise or waive such confidentiality, privilege
or exemption from disclosure as to this
communication.

If you have received this communication in error,
please notify the sender immediately and delete
this message from your system.


_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.
Reply | Threaded
Open this post in threaded view
|

Re: Wild bootstrap

braverock
In reply to this post by Paulo Grahl
On 03/29/2010 04:00 PM, Paulo Grahl wrote:
> I am wondering whether it is possible to use 'boot' package (or any
> other) in order to use the wild bootstrap method.
> Any help, examples, would be appreciated.
>    

There are many implementations of the wild bootstap in R.

Perhaps you should do a little searching, try a few things, and refine
your question with a code example.

Regards,

     - Brian

--
Brian G. Peterson
http://braverock.com/brian/
Ph: 773-459-4973
IM: bgpbraverock

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.
Reply | Threaded
Open this post in threaded view
|

Re: Wild bootstrap

Patrick Burns-2
It is good if the original poster explains what
a term means that they are searching for.  That
has at least two benefits:

* it avoids misunderstandings if the same or a
similar term has a different meaning.

* it educates subscribers (like me) who don't
know the term.

If not the original poster, then it's nice if a
response contains it.  So here goes:

The wild bootstrap is bootstrapping residuals and
then randomly multiplying by 1 or -1.  Hence ensuring
the distribution is symmetric around zero.

I've done it -- I just didn't know it had a name.

The bootstrapping tutorial on www.burns-stat.com
would tell you how to do it yourself (minus the last
step of multiplying by -1 or 1).


On 29/03/2010 22:08, Brian G. Peterson wrote:

> On 03/29/2010 04:00 PM, Paulo Grahl wrote:
>> I am wondering whether it is possible to use 'boot' package (or any
>> other) in order to use the wild bootstrap method.
>> Any help, examples, would be appreciated.
>
> There are many implementations of the wild bootstap in R.
>
> Perhaps you should do a little searching, try a few things, and refine
> your question with a code example.
>
> Regards,
>
> - Brian
>

--
Patrick Burns
[hidden email]
http://www.burns-stat.com

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.
Reply | Threaded
Open this post in threaded view
|

Re: Wild bootstrap

Jae Kim-3
The wild bootstrap is bootstrapping for heteroskedastic data.

The package vrtest has wild bootstrap implementations of the variance ratio
tests and you will find some references in the manual.

A well-known reference is

Davidson, Russell & Flachaire, Emmanuel, 2008. "The wild bootstrap, tamed at
last," Journal of Econometrics, Elsevier, vol. 146(1), pages 162-169,
September

It is not intended for symmetry, but for replicating heteroskdastic
structure.

It also has wide applications to financial data.

Hope this helps. Jae Kim




--------------------------------------------------
From: "Patrick Burns" <[hidden email]>
Sent: Tuesday, March 30, 2010 7:14 PM
To: <[hidden email]>
Subject: Re: [R-SIG-Finance] Wild bootstrap

> It is good if the original poster explains what
> a term means that they are searching for.  That
> has at least two benefits:
>
> * it avoids misunderstandings if the same or a
> similar term has a different meaning.
>
> * it educates subscribers (like me) who don't
> know the term.
>
> If not the original poster, then it's nice if a
> response contains it.  So here goes:
>
> The wild bootstrap is bootstrapping residuals and
> then randomly multiplying by 1 or -1.  Hence ensuring
> the distribution is symmetric around zero.
>
> I've done it -- I just didn't know it had a name.
>
> The bootstrapping tutorial on www.burns-stat.com
> would tell you how to do it yourself (minus the last
> step of multiplying by -1 or 1).
>
>
> On 29/03/2010 22:08, Brian G. Peterson wrote:
>> On 03/29/2010 04:00 PM, Paulo Grahl wrote:
>>> I am wondering whether it is possible to use 'boot' package (or any
>>> other) in order to use the wild bootstrap method.
>>> Any help, examples, would be appreciated.
>>
>> There are many implementations of the wild bootstap in R.
>>
>> Perhaps you should do a little searching, try a few things, and refine
>> your question with a code example.
>>
>> Regards,
>>
>> - Brian
>>
>
> --
> Patrick Burns
> [hidden email]
> http://www.burns-stat.com
>
> _______________________________________________
> [hidden email] mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only. If you want to post, subscribe first.
> -- Also note that this is not the r-help list where general R questions
> should go.
>

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.
Reply | Threaded
Open this post in threaded view
|

Re: Wild bootstrap

Matthieu Stigler
In reply to this post by Patrick Burns-2

Actually the wild bootstrap just samples the residuals, following
different schemes:
- 1 and -1 ("rademacher" bootstrap)
-normal distribution
-other schemes... see
http://www.econ.queensu.ca/working_papers/papers/qed_wp_1028.pdf

I have implemented such a bootstrap for VAR models (allowing to include
HC estimators from pkg sandwich), see:
library(vars)
?causality

Note that as only the residuals are bootstraped, and not the regressors,
a lot of computation can be saved as you don't need to compute every
time the (X'X)-1 matrix. Because you want to do it many times, it can be
useful not to reuse lm() at each step

I explored:
update(lm)
and finally used something like:
Ynew<-pred+res*rnorm(n=obs, mean=0, sd=x)
PI.boot<-solve(cross, crossprod(Zmlm,Ynew))

But this sure could be more efficient...

Matthieu



Patrick Burns a écrit :

> It is good if the original poster explains what
> a term means that they are searching for.  That
> has at least two benefits:
>
> * it avoids misunderstandings if the same or a
> similar term has a different meaning.
>
> * it educates subscribers (like me) who don't
> know the term.
>
> If not the original poster, then it's nice if a
> response contains it.  So here goes:
>
> The wild bootstrap is bootstrapping residuals and
> then randomly multiplying by 1 or -1.  Hence ensuring
> the distribution is symmetric around zero.
>
> I've done it -- I just didn't know it had a name.
>
> The bootstrapping tutorial on www.burns-stat.com
> would tell you how to do it yourself (minus the last
> step of multiplying by -1 or 1).
>
>
> On 29/03/2010 22:08, Brian G. Peterson wrote:
>> On 03/29/2010 04:00 PM, Paulo Grahl wrote:
>>> I am wondering whether it is possible to use 'boot' package (or any
>>> other) in order to use the wild bootstrap method.
>>> Any help, examples, would be appreciated.
>>
>> There are many implementations of the wild bootstap in R.
>>
>> Perhaps you should do a little searching, try a few things, and refine
>> your question with a code example.
>>
>> Regards,
>>
>> - Brian
>>
>

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.
Reply | Threaded
Open this post in threaded view
|

Re: Wild bootstrap

Paulo Grahl
Thank you all for the help.  And sorry for not being precise on the
question, but you got it right:
my question was regarding the wild bootstrap for bootstrapping
heteroskedastic data, using Rademacher random variables. Even though
it is simple to implement it, I was wondering whether or not that
could be done
in a straightforward way using the 'boot' package.
Thanks
Paulo

On Tue, Mar 30, 2010 at 5:39 AM, Matthieu Stigler
<[hidden email]> wrote:

>
> Actually the wild bootstrap just samples the residuals, following different
> schemes:
> - 1 and -1 ("rademacher" bootstrap)
> -normal distribution
> -other schemes... see
> http://www.econ.queensu.ca/working_papers/papers/qed_wp_1028.pdf
>
> I have implemented such a bootstrap for VAR models (allowing to include HC
> estimators from pkg sandwich), see:
> library(vars)
> ?causality
>
> Note that as only the residuals are bootstraped, and not the regressors, a
> lot of computation can be saved as you don't need to compute every time the
> (X'X)-1 matrix. Because you want to do it many times, it can be useful not
> to reuse lm() at each step
>
> I explored:
> update(lm)
> and finally used something like:
> Ynew<-pred+res*rnorm(n=obs, mean=0, sd=x)
> PI.boot<-solve(cross, crossprod(Zmlm,Ynew))
>
> But this sure could be more efficient...
>
> Matthieu
>
>
>
> Patrick Burns a écrit :
>>
>> It is good if the original poster explains what
>> a term means that they are searching for.  That
>> has at least two benefits:
>>
>> * it avoids misunderstandings if the same or a
>> similar term has a different meaning.
>>
>> * it educates subscribers (like me) who don't
>> know the term.
>>
>> If not the original poster, then it's nice if a
>> response contains it.  So here goes:
>>
>> The wild bootstrap is bootstrapping residuals and
>> then randomly multiplying by 1 or -1.  Hence ensuring
>> the distribution is symmetric around zero.
>>
>> I've done it -- I just didn't know it had a name.
>>
>> The bootstrapping tutorial on www.burns-stat.com
>> would tell you how to do it yourself (minus the last
>> step of multiplying by -1 or 1).
>>
>>
>> On 29/03/2010 22:08, Brian G. Peterson wrote:
>>>
>>> On 03/29/2010 04:00 PM, Paulo Grahl wrote:
>>>>
>>>> I am wondering whether it is possible to use 'boot' package (or any
>>>> other) in order to use the wild bootstrap method.
>>>> Any help, examples, would be appreciated.
>>>
>>> There are many implementations of the wild bootstap in R.
>>>
>>> Perhaps you should do a little searching, try a few things, and refine
>>> your question with a code example.
>>>
>>> Regards,
>>>
>>> - Brian
>>>
>>
>
>



--
Paulo Gustavo Grahl, CFA
------------------------------------------
[hidden email]
[hidden email]
www.linkedin.com/in/pgrahl

_______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only. If you want to post, subscribe first.
-- Also note that this is not the r-help list where general R questions should go.