[R-SIG-Finance] [R-sig-finance] troubles with the weights in the VaR function

genx info at genetrix.se
Thu Apr 26 14:55:11 CEST 2007


I have the same problem with vectors of different length, most packages don't
know how to scale and adjust timeseries / vectors of different length. It
would be a welcome contribution to R Finance if any programmer out there
could solve this problem in an easy way.


Manu do a dim(vector) to check length of your vectors / matrices that you
want to compare. As an example, if i want to calculate the annualized
standard deviation (sigma) for n-periods i do the following on each vector,
this example vector is days.

sd(vector[(length(vector)-n):length(vector)]) * sqrt(252)



Kind regards
genx, Dura Mater



manu-25 wrote:
> 
> hi there
> 
> i have some troubles with VaR ( value at risk function)
> to be more specific, with the weights in the VaR function
> 
> 
> when i run the example:
> equalWeights = rep(1/4, 4)
> alpha = 0.10
> # Value at Risk:
> VaR(myAssets, equalWeights, alpha)
> 
> everything is ok
> 
> 
> 
> BUT 
> 
> when i read my own data set, and try to have my own weights, i have the
> following message :
> 
> Erreur dans `names<-.default`(`*tmp*`, value = "VaR") : 
>         attribut 'names' [1] doit être de même longueur que le vecteur [0]
> 
> which can be translated as:
> 
> error in `names<-.default`(`*tmp*`, value = "VaR") : 
> 	attribute 'names' [1] must have the same length as vector [0]
> 
> 
> 
> i have no idea of what it means
> :-(
> 
> 
> i printed the names of my data, and it was exactely the same as the names
> in the VaR example
> 
> 
> 
> when returning this message, R returns at the same time the computation of
> the VaR, but using the default (equal weights); in my case it is not
> possible to have different weights :-(
> 
> 
> 
> 
> did anyone face the same problem?
> if yes, how to solve it
> 
> 
> thx in advance
> 
> 
> regards
> 
> 
> manu
> 
> _______________________________________________
> R-SIG-Finance at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-finance
> 
> 

-- 
View this message in context: http://www.nabble.com/troubles-with-the-weights-in-the-VaR-function-tf2785155.html#a10199718
Sent from the Rmetrics mailing list archive at Nabble.com.



More information about the R-SIG-Finance mailing list