HJM model (Interest rate)

[Ana Patricia Martins-2]

**

Dears users,

Although my basic training is in statistics, I've little knowledge about
interest rates models, and it was suggested Cox-Ingersoll-Ross process,
Ornstein-Uhlenbeck or Vasicek process or Heath-Jarrow-Morton methods.

Does anyone know if exist HJM model in R? I can't find…

The CIR model was considered, however based on the observed data (1998-2007)
doesn't works.
Does anyone can suggest a package or other models?

Thanks in advance your help.
Best regards
Ana Patrícia

        [[alternative HTML version deleted]]


_______________________________________________
R-SIG-Finance@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only.
-- If you want to post, subscribe first.

[statquant]

I don't own the book so I can't say anything about it's quality but it (
see link below ) must point to packages involving such things ?
also, there is a package listing at www.r-project.org that may describe
such a package ? or even do an R archive search for Stefan Iacus,
the author of the book.

 
http://www.amazon.com/Simulation-Inference-Stochastic-Differential-Equations/dp/0387758380/ref=sr_1_3?ie=UTF8&s=books&qid=1212090213&sr=8-3


On Thu, May 29, 2008 at  3:36 PM, Ana Patricia Martins wrote:

> **
>
> Dears users,
>
> Although my basic training is in statistics, I've little knowledge
> about
> interest rates models, and it was suggested Cox-Ingersoll-Ross
> process,
> Ornstein-Uhlenbeck or Vasicek process or Heath-Jarrow-Morton methods.
>
> Does anyone know if exist HJM model in R? I can't find�
>
> The CIR model was considered, however based on the observed data
> (1998-2007)
> doesn't works.
> Does anyone can suggest a package or other models?
>
> Thanks in advance your help.
> Best regards
> Ana Patr�cia
>
> [[alternative HTML version deleted]]
>
>
>
>      ------------------------------
>
> _______________________________________________
> R-SIG-Finance@... mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only.
> -- If you want to post, subscribe first.

_______________________________________________
R-SIG-Finance@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only.
-- If you want to post, subscribe first.

[Dale Smith-5]

I would say look at the Hull-White model. They even wrote a paper outlining how to implement their model, a rarity for academics. Just go to John Hull or Alan White's web page and look for the paper, or Google for it.

Christopher Finger's group at Riskmetrics recommended using this model in the MBS space. Register at the Riskmetrics web site & look for the article in 2004 or 2005.

HJM can be difficult to calibrate.

Dale Smith, Ph.D.
Vicis Capital LLC
Voice: 212-909-4635
Email: dsmith@...
AIM: dsmith11701

-----Original Message-----
From: r-sig-finance-bounces@... [mailto:r-sig-finance-bounces@...] On Behalf Of markleeds@...
Sent: Thursday, May 29, 2008 3:47 PM
To: Ana Patricia Martins
Cc: r-sig-finance@...
Subject: Re: [R-SIG-Finance] HJM model (Interest rate)

I don't own the book so I can't say anything about it's quality but it (
see link below ) must point to packages involving such things ?
also, there is a package listing at www.r-project.org that may describe
such a package ? or even do an R archive search for Stefan Iacus,
the author of the book.

 
http://www.amazon.com/Simulation-Inference-Stochastic-Differential-Equations/dp/0387758380/ref=sr_1_3?ie=UTF8&s=books&qid=1212090213&sr=8-3


On Thu, May 29, 2008 at  3:36 PM, Ana Patricia Martins wrote:

> **
>
> Dears users,
>
> Although my basic training is in statistics, I've little knowledge
> about
> interest rates models, and it was suggested Cox-Ingersoll-Ross
> process,
> Ornstein-Uhlenbeck or Vasicek process or Heath-Jarrow-Morton methods.
>
> Does anyone know if exist HJM model in R? I can't find�
>
> The CIR model was considered, however based on the observed data
> (1998-2007)
> doesn't works.
> Does anyone can suggest a package or other models?
>
> Thanks in advance your help.
> Best regards
> Ana Patr�cia
>
> [[alternative HTML version deleted]]
>
>
>
>      ------------------------------
>
> _______________________________________________
> R-SIG-Finance@... mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only.
> -- If you want to post, subscribe first.

_______________________________________________
R-SIG-Finance@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only.
-- If you want to post, subscribe first.

All e-mail sent to or from this address will be received or otherwise recorded by Vicis Capital, LLC and is subject to archival, monitoring and/or review, by and/or disclosure to, someone other than the recipient.  This message is intended only for the use of the person(s) ("intended recipient") to whom it is addressed.  It may contain information that is privileged and confidential.  If you are not the intended recipient, please contact the sender as soon as possible and delete the message without reading it or making a copy.  Any dissemination, distribution, copying, or other use of this message or any of its content by any person other than the intended recipient is strictly prohibited.  Vicis Capital, LLC only transacts business in states where it is properly registered or notice filed, or excluded or exempted from registration or notice filing requirements.
_______________________________________________
R-SIG-Finance@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only.
-- If you want to post, subscribe first.

[Brian G. Peterson]

Ana Patricia Martins wrote:

> Although my basic training is in statistics, I've little knowledge about
> interest rates models, and it was suggested Cox-Ingersoll-Ross process,
> Ornstein-Uhlenbeck or Vasicek process or Heath-Jarrow-Morton methods.
>
> Does anyone know if exist HJM model in R? I can't find…
>
> The CIR model was considered, however based on the observed data (1998-2007)
> doesn't works.
> Does anyone can suggest a package or other models?
>
> Thanks in advance your help.
> Best regards
> Ana Patrícia

Sorry for my late reply here, but here are some packages or sources you
should consider:


The package 'termstrc' contains functions for computing bond prices of
many different types of bonds, as well as parametric, spline, and
Nelson-Siegel term structure models

The package 'fBonds' from RMetrics contains functions for Nelson-Siegel
and Nelson-Siegel-Svensson term structure models

The package 'sde' implements the Ornstein-Uhlenbeck or Vasicek model

The package 'pomp' uses Markov processes to simulate univariate and
bivariate Ornstein-Uhlenbeck or Vasicek processes.

The package 'SemiPar' implements semiparametric spline models, including
the Jarrow-Ruppert-Yu term structure model.

Chapter 9 of David Ruppert's "Statistics in Finance" covers fixed income
models, and his examples have all been re-worked in R and are available
on the internet.

I'm sure that there are more, but these are the ones that come
immediately to mind.  I am *not* aware of an R implementation of a
Heath-Jarrow-Morton method, but that doesn't mean that one doesn't exist
or couldn't be readily created.

Regards,

   - Brian

_______________________________________________
R-SIG-Finance@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only.
-- If you want to post, subscribe first.

[Thomas Steiner]

I agree, very good directions to go.

Just as personal code, I craeted this and some other pictures for
wikipedia: http://commons.wikimedia.org/wiki/Image:Zins-Vasicek.png
where you find the R code as well. let me know if you need eg CIR or
others (jumps?) as well. (see Svensson at
http://commons.wikimedia.org/wiki/Image:Zinsstruktur.png, CIR at
http://commons.wikimedia.org/wiki/Image:SQRTDiffusion.png)

And HJM is a framework, not a model. You will decide something on the
shape of the forward rate curve (eg Svensson, but then the is just one
(!) source of randomness possible if you want to be consistent (too
complicated for me...).

Thomas


2008/6/4, Brian G. Peterson <brian@...>:

> Ana Patricia Martins wrote:
> > Although my basic training is in statistics, I've little knowledge about
> > interest rates models, and it was suggested Cox-Ingersoll-Ross process,
> > Ornstein-Uhlenbeck or Vasicek process or Heath-Jarrow-Morton methods.
> >
> > Does anyone know if exist HJM model in R? I can't find…
> >
> > The CIR model was considered, however based on the observed data
> (1998-2007)
> > doesn't works.
> > Does anyone can suggest a package or other models?
> >
> > Thanks in advance your help.
> > Best regards
> > Ana Patrícia
> >
>
>
> Sorry for my late reply here, but here are some packages or sources you
> should consider:
>
>
> The package 'termstrc' contains functions for computing bond prices of many
> different types of bonds, as well as parametric, spline, and Nelson-Siegel
> term structure models
>
> The package 'fBonds' from RMetrics contains functions for Nelson-Siegel and
> Nelson-Siegel-Svensson term structure models
>
> The package 'sde' implements the Ornstein-Uhlenbeck or Vasicek model
>
> The package 'pomp' uses Markov processes to simulate univariate and
> bivariate Ornstein-Uhlenbeck or Vasicek processes.
>
> The package 'SemiPar' implements semiparametric spline models, including the
> Jarrow-Ruppert-Yu term structure model.
>
> Chapter 9 of David Ruppert's "Statistics in Finance" covers fixed income
> models, and his examples have all been re-worked in R and are available on
> the internet.
>
> I'm sure that there are more, but these are the ones that come immediately
> to mind.  I am *not* aware of an R implementation of a Heath-Jarrow-Morton
> method, but that doesn't mean that one doesn't exist or couldn't be readily
> created.
>
> Regards,
>
>  - Brian
>
>
> _______________________________________________
> R-SIG-Finance@... mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> -- Subscriber-posting only.
> -- If you want to post, subscribe first.
>

_______________________________________________
R-SIG-Finance@... mailing list
https://stat.ethz.ch/mailman/listinfo/r-sig-finance
-- Subscriber-posting only.
-- If you want to post, subscribe first.