Re: agg monthly returns

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

Re: agg monthly returns

Kenton Russell
So glad you read my post.  Hate that I could not share index history.

2 suggestions:
1) using ROC default is continuous, try type="discrete"

BarAggReturn <- ROC((to.monthly(AGG)), type="discrete")*100

2) also, since AGG history is limited, use a mutual fund like vbmfx for more history

Hope this helps.

Kent Russell
http://timelyportfolio.blogspot.com


In reply to:
  1. Calculate AGG monthly returns using Quantmod (Pacheco, Luis)
After reading the great post "Bond Market as a Casino Game Part 1" in
the Timely Portfolio blog,

(http://timelyportfolio.blogspot.com/2011/04/bond-market-as-casino-game-
part-1.html)

I tried to replicate the monthly returns that iShares is publishing
here:

(http://us.ishares.com/product_info/fund/excel_historicalperformance.htm
?ticker=AGG)

using quantmod, but the results for the Adjusted close column are very
different



getSymbols("AGG")

BarAggReturn <- ROC((to.monthly(AGG)))*100



Some comparisons:



Month

Return using ROC on Adjusted

iShares

Nov-10

-0.83966718

-0.56

Dec-10

-0.67493958

-1.07

Jan-11

-0.08588197

0.07

Feb-11

0.285986849

0.23



Thanks for all your help, I deeply appreciate it.







Luis Pacheco

Asurion



        [[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.
Reply | Threaded
Open this post in threaded view
|

Vasicek,CIR or RiskMetrics

troger19

Hello researchers

Do you have some experience with risk measurement by Vasicek, CIR models or geometric Brownian distribution? Are there any R packages supporting these models?  
I found these 2 links, that are quite helpful
http://www.r-bloggers.com/basket-option-pricing-step-by-step/   
http://www.r-bloggers.com/fun-with-the-vasicek-interest-rate-model/

and I also searched ??? in R, but found only simulations.

I would like to model few currency pairs by mentioned models and consequently their future influence on costs, revenues and sales. Or can you point off some better techniques,solutions or references for modeling corporate risk  in R?
Thank you very much.

_______________________________________________
[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: Vasicek,CIR or RiskMetrics

Eric Zivot
Check out the sde package and the very nice book by Stefano Iacus that goes
with it

http://www.amazon.com/Simulation-Inference-Stochastic-Differential-Equations
/dp/1441926070/ref=sr_1_1?ie=UTF8&s=books&qid=1302194109&sr=8-1


-----Original Message-----
From: [hidden email]
[mailto:[hidden email]] On Behalf Of [hidden email]
Sent: Thursday, April 07, 2011 9:33 AM
To: [hidden email]
Subject: [R-SIG-Finance] Vasicek,CIR or RiskMetrics


Hello researchers

Do you have some experience with risk measurement by Vasicek, CIR models or
geometric Brownian distribution? Are there any R packages supporting these
models?  
I found these 2 links, that are quite helpful
http://www.r-bloggers.com/basket-option-pricing-step-by-step/   
http://www.r-bloggers.com/fun-with-the-vasicek-interest-rate-model/

and I also searched ??? in R, but found only simulations.

I would like to model few currency pairs by mentioned models and
consequently their future influence on costs, revenues and sales. Or can you
point off some better techniques,solutions or references for modeling
corporate risk  in R?
Thank you very much.

_______________________________________________
[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: Vasicek,CIR or RiskMetrics

Sarbo
In reply to this post by troger19
Hi,

There are lots of packages within R that support all of these
distributions. The Rmetrics suite is very good; RQuantLib has option
valuation functions that are very useful; and the quantmod suite is also
exceptionally good.

Why, though, are you using Vasicek or CIR models to model currency
pairs? These models are not arbitrage-free and do not correspond well to
market-observable term structures. Nor do they incorporate anything
other than static assumptions about volatility. There are better models
out there for dealing with currencies.

On Thu, 2011-04-07 at 18:32 +0200, [hidden email] wrote:

> Hello researchers
>
> Do you have some experience with risk measurement by Vasicek, CIR models or geometric Brownian distribution? Are there any R packages supporting these models?  
> I found these 2 links, that are quite helpful
> http://www.r-bloggers.com/basket-option-pricing-step-by-step/   
> http://www.r-bloggers.com/fun-with-the-vasicek-interest-rate-model/
>
> and I also searched ??? in R, but found only simulations.
>
> I would like to model few currency pairs by mentioned models and consequently their future influence on costs, revenues and sales. Or can you point off some better techniques,solutions or references for modeling corporate risk  in R?
> Thank you very much.
>
> _______________________________________________
> [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.