Quantcast

Simulating paths in rmgarch

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
9 messages Options
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Simulating paths in rmgarch

Josh Segal
Hi everyone,

I'm trying to use the rmgarch package to estimate a multivariate GARCH
model and then use those parameters to simulate paths forward.  I've gotten
as far as creating a goGARCHsim object (for example), but can't figure out
how to access the simulated returns.  I've looked through all the methods
described in the documentation (page 58) but don't see anything relevant.
I believe I am able to do this in the univariate case with rugarch - is it
not possible in rmgarch?

Thanks for your help!

        [[alternative HTML version deleted]]

_______________________________________________
[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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

alexios
library(rmgarch)
data("dji30ret")
spec<-gogarchspec(mean.model=list(model="AR"),ica = "radical")
fit=gogarchfit(spec,dji30ret[,1:5])
sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod = "sample",rseed = 10)

head(sim@msim$seriesSim[[1]])
str(sim@msim)

There are lots of examples and demos in the /inst/rmgarch.tests/ folder
of the source package.

Alexios

On 3/22/2017 2:54 PM, Josh Segal wrote:

> Hi everyone,
>
> I'm trying to use the rmgarch package to estimate a multivariate GARCH
> model and then use those parameters to simulate paths forward.  I've gotten
> as far as creating a goGARCHsim object (for example), but can't figure out
> how to access the simulated returns.  I've looked through all the methods
> described in the documentation (page 58) but don't see anything relevant.
> I believe I am able to do this in the univariate case with rugarch - is it
> not possible in rmgarch?
>
> Thanks for your help!
>
> [[alternative HTML version deleted]]
>
> _______________________________________________
> [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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

Josh Segal
Alexios,

Thanks again for your help.
I'm getting some counterintuitive results with the seriesSim output.  When
I run your exact example above and then compute cor(sim@msim$seriesSim[[1]]),
I get a correlation matrix that has non-diagonal values close to zero
(ranging from -0.10 to 0.08).
When I measure the correlation of the original data (cor(dji30ret[,1:5])) I
get values from 0.33 to 0.66.
Shouldn't the simulation demonstrate higher unconditional correlations?  Am
I misunderstanding something about the package, or does this indicate a
problem?

Thanks,
Josh

On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos <[hidden email]>
wrote:

> library(rmgarch)
> data("dji30ret")
> spec<-gogarchspec(mean.model=list(model="AR"),ica = "radical")
> fit=gogarchfit(spec,dji30ret[,1:5])
> sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod = "sample",rseed = 10)
>
> head(sim@msim$seriesSim[[1]])
> str(sim@msim)
>
> There are lots of examples and demos in the /inst/rmgarch.tests/ folder of
> the source package.
>
> Alexios
>
>
> On 3/22/2017 2:54 PM, Josh Segal wrote:
>
>> Hi everyone,
>>
>> I'm trying to use the rmgarch package to estimate a multivariate GARCH
>> model and then use those parameters to simulate paths forward.  I've
>> gotten
>> as far as creating a goGARCHsim object (for example), but can't figure out
>> how to access the simulated returns.  I've looked through all the methods
>> described in the documentation (page 58) but don't see anything relevant.
>> I believe I am able to do this in the univariate case with rugarch - is it
>> not possible in rmgarch?
>>
>> Thanks for your help!
>>
>>         [[alternative HTML version deleted]]
>>
>> _______________________________________________
>> [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.
>

        [[alternative HTML version deleted]]

_______________________________________________
[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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

alexios
Try using model="VAR" instead of "AR"....will check to see if something
is amiss otherwise.

A.

On 24/03/2017 13:42, Josh Segal wrote:

> Alexios,
>
> Thanks again for your help.
> I'm getting some counterintuitive results with the seriesSim output.
> When I run your exact example above and then compute
> cor(sim@msim$seriesSim[[1]]), I get a correlation matrix that has
> non-diagonal values close to zero (ranging from -0.10 to 0.08).  
> When I measure the correlation of the original data
> (cor(dji30ret[,1:5])) I get values from 0.33 to 0.66.
> Shouldn't the simulation demonstrate higher unconditional
> correlations?  Am I misunderstanding something about the package, or
> does this indicate a problem?
>
> Thanks,
> Josh
>
> On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos <[hidden email]
> <mailto:[hidden email]>> wrote:
>
>     library(rmgarch)
>     data("dji30ret")
>     spec<-gogarchspec(mean.model=list(model="AR"),ica = "radical")
>     fit=gogarchfit(spec,dji30ret[,1:5])
>     sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod =
>     "sample",rseed = 10)
>
>     head(sim@msim$seriesSim[[1]])
>     str(sim@msim)
>
>     There are lots of examples and demos in the /inst/rmgarch.tests/
>     folder of the source package.
>
>     Alexios
>
>
>     On 3/22/2017 2:54 PM, Josh Segal wrote:
>
>         Hi everyone,
>
>         I'm trying to use the rmgarch package to estimate a
>         multivariate GARCH
>         model and then use those parameters to simulate paths
>         forward.  I've gotten
>         as far as creating a goGARCHsim object (for example), but
>         can't figure out
>         how to access the simulated returns.  I've looked through all
>         the methods
>         described in the documentation (page 58) but don't see
>         anything relevant.
>         I believe I am able to do this in the univariate case with
>         rugarch - is it
>         not possible in rmgarch?
>
>         Thanks for your help!
>
>                 [[alternative HTML version deleted]]
>
>         _______________________________________________
>         [hidden email]
>         <mailto:[hidden email]> mailing list
>         https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>         <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] <mailto:[hidden email]>
>     mailing list
>     https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>     <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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

Josh Segal
VAR seems ok, while AR and constant are not

Should I only use VAR with GOGARCH?

On Fri, Mar 24, 2017 at 3:43 PM, alexios galanos <[hidden email]>
wrote:

> Try using model="VAR" instead of "AR"....will check to see if something
> is amiss otherwise.
>
> A.
>
> On 24/03/2017 13:42, Josh Segal wrote:
> > Alexios,
> >
> > Thanks again for your help.
> > I'm getting some counterintuitive results with the seriesSim output.
> > When I run your exact example above and then compute
> > cor(sim@msim$seriesSim[[1]]), I get a correlation matrix that has
> > non-diagonal values close to zero (ranging from -0.10 to 0.08).
> > When I measure the correlation of the original data
> > (cor(dji30ret[,1:5])) I get values from 0.33 to 0.66.
> > Shouldn't the simulation demonstrate higher unconditional
> > correlations?  Am I misunderstanding something about the package, or
> > does this indicate a problem?
> >
> > Thanks,
> > Josh
> >
> > On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos <[hidden email]
> > <mailto:[hidden email]>> wrote:
> >
> >     library(rmgarch)
> >     data("dji30ret")
> >     spec<-gogarchspec(mean.model=list(model="AR"),ica = "radical")
> >     fit=gogarchfit(spec,dji30ret[,1:5])
> >     sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod =
> >     "sample",rseed = 10)
> >
> >     head(sim@msim$seriesSim[[1]])
> >     str(sim@msim)
> >
> >     There are lots of examples and demos in the /inst/rmgarch.tests/
> >     folder of the source package.
> >
> >     Alexios
> >
> >
> >     On 3/22/2017 2:54 PM, Josh Segal wrote:
> >
> >         Hi everyone,
> >
> >         I'm trying to use the rmgarch package to estimate a
> >         multivariate GARCH
> >         model and then use those parameters to simulate paths
> >         forward.  I've gotten
> >         as far as creating a goGARCHsim object (for example), but
> >         can't figure out
> >         how to access the simulated returns.  I've looked through all
> >         the methods
> >         described in the documentation (page 58) but don't see
> >         anything relevant.
> >         I believe I am able to do this in the univariate case with
> >         rugarch - is it
> >         not possible in rmgarch?
> >
> >         Thanks for your help!
> >
> >                 [[alternative HTML version deleted]]
> >
> >         _______________________________________________
> >         [hidden email]
> >         <mailto:[hidden email]> mailing list
> >         https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >         <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] <mailto:[hidden email]>
> >     mailing list
> >     https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >     <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.
> >
> >
>
>

        [[alternative HTML version deleted]]

_______________________________________________
[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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

alexios
Yes...will check this weekend to see whether something may have gone amiss in the AR/Constant simulation. Check my bitbucket repo by next week to see if any changes were committed and reinstall from there if so.


Alexios

> On Mar 24, 2017, at 3:40 PM, Josh Segal <[hidden email]> wrote:
>
> VAR seems ok, while AR and constant are not
>
> Should I only use VAR with GOGARCH?
>
>> On Fri, Mar 24, 2017 at 3:43 PM, alexios galanos <[hidden email]> wrote:
>> Try using model="VAR" instead of "AR"....will check to see if something
>> is amiss otherwise.
>>
>> A.
>>
>> On 24/03/2017 13:42, Josh Segal wrote:
>> > Alexios,
>> >
>> > Thanks again for your help.
>> > I'm getting some counterintuitive results with the seriesSim output.
>> > When I run your exact example above and then compute
>> > cor(sim@msim$seriesSim[[1]]), I get a correlation matrix that has
>> > non-diagonal values close to zero (ranging from -0.10 to 0.08).
>> > When I measure the correlation of the original data
>> > (cor(dji30ret[,1:5])) I get values from 0.33 to 0.66.
>> > Shouldn't the simulation demonstrate higher unconditional
>> > correlations?  Am I misunderstanding something about the package, or
>> > does this indicate a problem?
>> >
>> > Thanks,
>> > Josh
>> >
>> > On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos <[hidden email]
>> > <mailto:[hidden email]>> wrote:
>> >
>> >     library(rmgarch)
>> >     data("dji30ret")
>> >     spec<-gogarchspec(mean.model=list(model="AR"),ica = "radical")
>> >     fit=gogarchfit(spec,dji30ret[,1:5])
>> >     sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod =
>> >     "sample",rseed = 10)
>> >
>> >     head(sim@msim$seriesSim[[1]])
>> >     str(sim@msim)
>> >
>> >     There are lots of examples and demos in the /inst/rmgarch.tests/
>> >     folder of the source package.
>> >
>> >     Alexios
>> >
>> >
>> >     On 3/22/2017 2:54 PM, Josh Segal wrote:
>> >
>> >         Hi everyone,
>> >
>> >         I'm trying to use the rmgarch package to estimate a
>> >         multivariate GARCH
>> >         model and then use those parameters to simulate paths
>> >         forward.  I've gotten
>> >         as far as creating a goGARCHsim object (for example), but
>> >         can't figure out
>> >         how to access the simulated returns.  I've looked through all
>> >         the methods
>> >         described in the documentation (page 58) but don't see
>> >         anything relevant.
>> >         I believe I am able to do this in the univariate case with
>> >         rugarch - is it
>> >         not possible in rmgarch?
>> >
>> >         Thanks for your help!
>> >
>> >                 [[alternative HTML version deleted]]
>> >
>> >         _______________________________________________
>> >         [hidden email]
>> >         <mailto:[hidden email]> mailing list
>> >         https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>> >         <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] <mailto:[hidden email]>
>> >     mailing list
>> >     https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>> >     <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.
>> >
>> >
>>
>

        [[alternative HTML version deleted]]

_______________________________________________
[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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

Josh Segal
Will do, thanks again!

On Fri, Mar 24, 2017 at 5:17 PM, Alexios Ghalanos <[hidden email]>
wrote:

> Yes...will check this weekend to see whether something may have gone amiss
> in the AR/Constant simulation. Check my bitbucket repo by next week to see
> if any changes were committed and reinstall from there if so.
>
>
> Alexios
>
> On Mar 24, 2017, at 3:40 PM, Josh Segal <[hidden email]> wrote:
>
> VAR seems ok, while AR and constant are not
>
> Should I only use VAR with GOGARCH?
>
> On Fri, Mar 24, 2017 at 3:43 PM, alexios galanos <[hidden email]>
> wrote:
>
>> Try using model="VAR" instead of "AR"....will check to see if something
>> is amiss otherwise.
>>
>> A.
>>
>> On 24/03/2017 13:42, Josh Segal wrote:
>> > Alexios,
>> >
>> > Thanks again for your help.
>> > I'm getting some counterintuitive results with the seriesSim output.
>> > When I run your exact example above and then compute
>> > cor(sim@msim$seriesSim[[1]]), I get a correlation matrix that has
>> > non-diagonal values close to zero (ranging from -0.10 to 0.08).
>> > When I measure the correlation of the original data
>> > (cor(dji30ret[,1:5])) I get values from 0.33 to 0.66.
>> > Shouldn't the simulation demonstrate higher unconditional
>> > correlations?  Am I misunderstanding something about the package, or
>> > does this indicate a problem?
>> >
>> > Thanks,
>> > Josh
>> >
>> > On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos <[hidden email]
>> > <mailto:[hidden email]>> wrote:
>> >
>> >     library(rmgarch)
>> >     data("dji30ret")
>> >     spec<-gogarchspec(mean.model=list(model="AR"),ica = "radical")
>> >     fit=gogarchfit(spec,dji30ret[,1:5])
>> >     sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod =
>> >     "sample",rseed = 10)
>> >
>> >     head(sim@msim$seriesSim[[1]])
>> >     str(sim@msim)
>> >
>> >     There are lots of examples and demos in the /inst/rmgarch.tests/
>> >     folder of the source package.
>> >
>> >     Alexios
>> >
>> >
>> >     On 3/22/2017 2:54 PM, Josh Segal wrote:
>> >
>> >         Hi everyone,
>> >
>> >         I'm trying to use the rmgarch package to estimate a
>> >         multivariate GARCH
>> >         model and then use those parameters to simulate paths
>> >         forward.  I've gotten
>> >         as far as creating a goGARCHsim object (for example), but
>> >         can't figure out
>> >         how to access the simulated returns.  I've looked through all
>> >         the methods
>> >         described in the documentation (page 58) but don't see
>> >         anything relevant.
>> >         I believe I am able to do this in the univariate case with
>> >         rugarch - is it
>> >         not possible in rmgarch?
>> >
>> >         Thanks for your help!
>> >
>> >                 [[alternative HTML version deleted]]
>> >
>> >         _______________________________________________
>> >         [hidden email]
>> >         <mailto:[hidden email]> mailing list
>> >         https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>> >         <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] <mailto:[hidden email]>
>> >     mailing list
>> >     https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>> >     <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.
>> >
>> >
>>
>>
>

        [[alternative HTML version deleted]]

_______________________________________________
[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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

alexios
Josh, I've pushed a fix to the repo. Try downloading now and
re-installing. Apparently the returned matrix was
constructed badly, aligning the vectors by row rather than by
column...good catch. I'll try to spend some time this
weekend conducting a general overview of the package which I've not
looked at for some time and also release to
CRAN soon the new version (of this and related) to also fix the issue
which has recently been cropping up on the
checks related to the registration of 'native routines'.

Cheers,

Alexios

On 24/03/2017 16:55, Josh Segal wrote:

> Will do, thanks again!
>
> On Fri, Mar 24, 2017 at 5:17 PM, Alexios Ghalanos <[hidden email]
> <mailto:[hidden email]>> wrote:
>
>     Yes...will check this weekend to see whether something may have
>     gone amiss in the AR/Constant simulation. Check my bitbucket repo
>     by next week to see if any changes were committed and reinstall
>     from there if so.
>
>
>     Alexios
>
>     On Mar 24, 2017, at 3:40 PM, Josh Segal <[hidden email]
>     <mailto:[hidden email]>> wrote:
>
>>     VAR seems ok, while AR and constant are not
>>
>>     Should I only use VAR with GOGARCH?
>>
>>     On Fri, Mar 24, 2017 at 3:43 PM, alexios galanos
>>     <[hidden email] <mailto:[hidden email]>> wrote:
>>
>>         Try using model="VAR" instead of "AR"....will check to see if
>>         something
>>         is amiss otherwise.
>>
>>         A.
>>
>>         On 24/03/2017 13:42, Josh Segal wrote:
>>         > Alexios,
>>         >
>>         > Thanks again for your help.
>>         > I'm getting some counterintuitive results with the
>>         seriesSim output.
>>         > When I run your exact example above and then compute
>>         > cor(sim@msim$seriesSim[[1]]), I get a correlation matrix
>>         that has
>>         > non-diagonal values close to zero (ranging from -0.10 to 0.08).
>>         > When I measure the correlation of the original data
>>         > (cor(dji30ret[,1:5])) I get values from 0.33 to 0.66.
>>         > Shouldn't the simulation demonstrate higher unconditional
>>         > correlations?  Am I misunderstanding something about the
>>         package, or
>>         > does this indicate a problem?
>>         >
>>         > Thanks,
>>         > Josh
>>         >
>>         > On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos
>>         <[hidden email] <mailto:[hidden email]>
>>         > <mailto:[hidden email] <mailto:[hidden email]>>>
>>         wrote:
>>         >
>>         >     library(rmgarch)
>>         >     data("dji30ret")
>>         >     spec<-gogarchspec(mean.model=list(model="AR"),ica =
>>         "radical")
>>         >     fit=gogarchfit(spec,dji30ret[,1:5])
>>         >     sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod =
>>         >     "sample",rseed = 10)
>>         >
>>         >     head(sim@msim$seriesSim[[1]])
>>         >     str(sim@msim)
>>         >
>>         >     There are lots of examples and demos in the
>>         /inst/rmgarch.tests/
>>         >     folder of the source package.
>>         >
>>         >     Alexios
>>         >
>>         >
>>         >     On 3/22/2017 2:54 PM, Josh Segal wrote:
>>         >
>>         >         Hi everyone,
>>         >
>>         >         I'm trying to use the rmgarch package to estimate a
>>         >         multivariate GARCH
>>         >         model and then use those parameters to simulate paths
>>         >         forward.  I've gotten
>>         >         as far as creating a goGARCHsim object (for
>>         example), but
>>         >         can't figure out
>>         >         how to access the simulated returns.  I've looked
>>         through all
>>         >         the methods
>>         >         described in the documentation (page 58) but don't see
>>         >         anything relevant.
>>         >         I believe I am able to do this in the univariate
>>         case with
>>         >         rugarch - is it
>>         >         not possible in rmgarch?
>>         >
>>         >         Thanks for your help!
>>         >
>>         >                 [[alternative HTML version deleted]]
>>         >
>>         >         _______________________________________________
>>         >         [hidden email]
>>         <mailto:[hidden email]>
>>         >         <mailto:[hidden email]
>>         <mailto:[hidden email]>> mailing list
>>         >         https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>>         <https://stat.ethz.ch/mailman/listinfo/r-sig-finance>
>>         >      
>>          <https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>>         <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]
>>         <mailto:[hidden email]>
>>         <mailto:[hidden email]
>>         <mailto:[hidden email]>>
>>         >     mailing list
>>         >     https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>>         <https://stat.ethz.ch/mailman/listinfo/r-sig-finance>
>>         >     <https://stat.ethz.ch/mailman/listinfo/r-sig-finance
>>         <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.
Threaded
Open this post in threaded view
|  
Report Content as Inappropriate

Re: Simulating paths in rmgarch

Josh Segal
The recent version works for me, thanks very much


On Fri, Mar 24, 2017 at 7:05 PM alexios galanos <[hidden email]> wrote:

> Josh, I've pushed a fix to the repo. Try downloading now and
> re-installing. Apparently the returned matrix was
> constructed badly, aligning the vectors by row rather than by
> column...good catch. I'll try to spend some time this
> weekend conducting a general overview of the package which I've not
> looked at for some time and also release to
> CRAN soon the new version (of this and related) to also fix the issue
> which has recently been cropping up on the
> checks related to the registration of 'native routines'.
>
> Cheers,
>
> Alexios
>
> On 24/03/2017 16:55, Josh Segal wrote:
> > Will do, thanks again!
> >
> > On Fri, Mar 24, 2017 at 5:17 PM, Alexios Ghalanos <[hidden email]
> > <mailto:[hidden email]>> wrote:
> >
> >     Yes...will check this weekend to see whether something may have
> >     gone amiss in the AR/Constant simulation. Check my bitbucket repo
> >     by next week to see if any changes were committed and reinstall
> >     from there if so.
> >
> >
> >     Alexios
> >
> >     On Mar 24, 2017, at 3:40 PM, Josh Segal <[hidden email]
> >     <mailto:[hidden email]>> wrote:
> >
> >>     VAR seems ok, while AR and constant are not
> >>
> >>     Should I only use VAR with GOGARCH?
> >>
> >>     On Fri, Mar 24, 2017 at 3:43 PM, alexios galanos
> >>     <[hidden email] <mailto:[hidden email]>> wrote:
> >>
> >>         Try using model="VAR" instead of "AR"....will check to see if
> >>         something
> >>         is amiss otherwise.
> >>
> >>         A.
> >>
> >>         On 24/03/2017 13:42, Josh Segal wrote:
> >>         > Alexios,
> >>         >
> >>         > Thanks again for your help.
> >>         > I'm getting some counterintuitive results with the
> >>         seriesSim output.
> >>         > When I run your exact example above and then compute
> >>         > cor(sim@msim$seriesSim[[1]]), I get a correlation matrix
> >>         that has
> >>         > non-diagonal values close to zero (ranging from -0.10 to
> 0.08).
> >>         > When I measure the correlation of the original data
> >>         > (cor(dji30ret[,1:5])) I get values from 0.33 to 0.66.
> >>         > Shouldn't the simulation demonstrate higher unconditional
> >>         > correlations?  Am I misunderstanding something about the
> >>         package, or
> >>         > does this indicate a problem?
> >>         >
> >>         > Thanks,
> >>         > Josh
> >>         >
> >>         > On Wed, Mar 22, 2017 at 4:06 PM, alexios galanos
> >>         <[hidden email] <mailto:[hidden email]>
> >>         > <mailto:[hidden email] <mailto:[hidden email]>>>
> >>         wrote:
> >>         >
> >>         >     library(rmgarch)
> >>         >     data("dji30ret")
> >>         >     spec<-gogarchspec(mean.model=list(model="AR"),ica =
> >>         "radical")
> >>         >     fit=gogarchfit(spec,dji30ret[,1:5])
> >>         >     sim=gogarchsim(fit,n.sim = 1000,m.sim=1,startMethod =
> >>         >     "sample",rseed = 10)
> >>         >
> >>         >     head(sim@msim$seriesSim[[1]])
> >>         >     str(sim@msim)
> >>         >
> >>         >     There are lots of examples and demos in the
> >>         /inst/rmgarch.tests/
> >>         >     folder of the source package.
> >>         >
> >>         >     Alexios
> >>         >
> >>         >
> >>         >     On 3/22/2017 2:54 PM, Josh Segal wrote:
> >>         >
> >>         >         Hi everyone,
> >>         >
> >>         >         I'm trying to use the rmgarch package to estimate a
> >>         >         multivariate GARCH
> >>         >         model and then use those parameters to simulate paths
> >>         >         forward.  I've gotten
> >>         >         as far as creating a goGARCHsim object (for
> >>         example), but
> >>         >         can't figure out
> >>         >         how to access the simulated returns.  I've looked
> >>         through all
> >>         >         the methods
> >>         >         described in the documentation (page 58) but don't see
> >>         >         anything relevant.
> >>         >         I believe I am able to do this in the univariate
> >>         case with
> >>         >         rugarch - is it
> >>         >         not possible in rmgarch?
> >>         >
> >>         >         Thanks for your help!
> >>         >
> >>         >                 [[alternative HTML version deleted]]
> >>         >
> >>         >         _______________________________________________
> >>         >         [hidden email]
> >>         <mailto:[hidden email]>
> >>         >         <mailto:[hidden email]
> >>         <mailto:[hidden email]>> mailing list
> >>         >         https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >>         <https://stat.ethz.ch/mailman/listinfo/r-sig-finance>
> >>         >
> >>          <https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >>         <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]
> >>         <mailto:[hidden email]>
> >>         <mailto:[hidden email]
> >>         <mailto:[hidden email]>>
> >>         >     mailing list
> >>         >     https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >>         <https://stat.ethz.ch/mailman/listinfo/r-sig-finance>
> >>         >     <https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> >>         <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.
> >>         >
> >>         >
> >>
> >>
> >
>
>

        [[alternative HTML version deleted]]

_______________________________________________
[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.
Loading...