[R-SIG-Finance] Back test report in Rugarch

[alexios ghalanos]

Have you checked your data and code carefully?
e.g. Does your data have 975+ points (875 for forecast and 100 for 
initializing the rolling estimation)?

I can't replicate your error and it is likely that you have forgotten 
something:

library(rugarch)
data(sp500ret)
spec=ugarchspec()
rollD2 = ugarchroll(spec, data = as.numeric(sp500ret[1:975,1]), n.ahead 
= 1, forecast.length = 875,
refit.every = 25, refit.window = "recursive", parallel = TRUE,
parallel.control = list(pkg = "snowfall", cores = 10), solver = "solnp",
solver.control = list(tol = 1e-05, delta = 1e-06, trace = 0),
calculate.VaR = TRUE, VaR.alpha = c(0.010, 0.05))

report(rollD2, type = "VaR", n.ahead = 1, VaR.alpha = 0.01, conf.level = 
0.95)
################################
Backtest Length:        875
################################

Please check your code VERY carefully before submitting.

-Alexios



On 02/05/2012 15:35, Papa sen wrote:
> Dear alexios and kerpel,
> Thanks so much for your comments. However, Alexios, I used the same
> codes and changed the backtest length =875 and yet got a report of 500
> to be the backtest length.
> Kind regards,
> p.s
>
> ------------------------------------------------------------------------
> *Da:* alexios ghalanos <alexios at 4dscape.com>
> *A:* Papa sen <papa.senyo at yahoo.it>
> *Cc:* "r-sig-finance at r-project.org" <r-sig-finance at r-project.org>
> *Inviato:* Mercoledì 2 Maggio 2012 15:49
> *Oggetto:* Re: [R-SIG-Finance] Back test report in Rugarch
>
> What are you having trouble understanding? The Null Hypothesis is
> clearly stated and the test also provides the 'decision' on whether to
> reject the Null at the given confidence level.
> Type ?VaRTest if you want a more detailed description of what each
> parameter means, or read the vignette for a description of what the test
> does with the literature reference.
> As to the backtest length "not changing", you do not state under which
> circumstances you experienced such as an error. From your code you
> requested a forecast length of 500 which is what you got in the
> resulting output.
>
> -Alexios
>
> On 02/05/2012 14:25, Papa sen wrote:
>  > Please find some sample codes:
>  > rollD = ugarchroll(spec4, data = as.numeric(ret), n.ahead = 1,
> forecast.length = 500,
>  > refit.every = 25, refit.window = "recursive", parallel = TRUE,
>  > parallel.control = list(pkg = "snowfall", cores = 10), solver = "solnp",
>  > solver.control = list(tol = 1e-05, delta = 1e-06, trace = 0),
>  > calculate.VaR = TRUE, VaR.alpha = c(0.010, 0.05))
>  >
>  > report(rollD, type = "VaR", n.ahead = 1, VaR.alpha = 0.01, conf.level
> = 0.95)
>  > report(rollD, type="fpm")
>  >
>  >
>  >
>  > ________________________________
>  > Da: John Kerpel<john.kerpel at gmail.com <mailto:john.kerpel at gmail.com>>
>  >
>  > Cc: "r-sig-finance at r-project.org
> <mailto:r-sig-finance at r-project.org>"<r-sig-finance at r-project.org
> <mailto:r-sig-finance at r-project.org>>
>  > Inviato: Mercoledì 2 Maggio 2012 15:09
>  > Oggetto: Re: [R-SIG-Finance] Back test report in Rugarch
>  >
>  >
>  > Are you using the ugarchroll method? Show some code...
>  >
>  >
>  >
>  >
>  > Dear all,
>  >> Please I did backtesting using rugarch and got the following.
> Finding it difficult to make sense of out of the result.
>  >> Please any help would be appreciated. I need some few comments. Also
> it appears that the backtest length does not change (i may be wrong)Find
> the output below:
>  >> VaR Backtest Report
>  >> ===========================================
>  >> Model: fGARCH-std
>  >> Backtest Length: 500
>  >> Data:
>  >> ==========================================
>  >> alpha: 1%
>  >> Expected Exceed: 5
>  >> Actual VaR Exceed: 4
>  >> Actual %: 0.8%
>  >> Unconditional Coverage (Kupiec)
>  >> Null-Hypothesis: Correct Exceedances
>  >> LR.uc Statistic: 0.217
>  >> LR.uc Critical: 3.841
>  >> LR.uc p-value: 0.641
>  >> Reject Null: NO
>  >> Conditional Coverage (Christoffersen)
>  >> Null-Hypothesis: Correct Exceedances&
>  >> Independence of Failures
>  >> LR.cc Statistic: 0.282
>  >> LR.cc Critical: 5.991
>  >> LR.cc p-value: 0.869
>  >> Reject Null: NO
>  >> kind regards,
>  >> paps
>  >> [[alternative HTML version deleted]]
>  >>
>  >>
>  >> _______________________________________________
>  >> R-SIG-Finance at r-project.org <mailto:R-SIG-Finance at r-project.org>
> 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]]
>  >
>  >
>  >
>  >
>  > _______________________________________________
>  > R-SIG-Finance at r-project.org <mailto:R-SIG-Finance at r-project.org>
> 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.
>
>
>