Re: modeling VARMA-Garch in R

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

Re: modeling VARMA-Garch in R

alexios
1. rmgarch does not support varma, only VAR
2. The model you estimated is univariate ARMA(1,1)
3. The NAs are because you set fit.control = list(eval.se = FALSE)
i.e. you are telling the routine to not evaluate the standard errors.

Alexios


> On Jul 25, 2018, at 16:08, Marcio Bernardo <[hidden email]> wrote:
>
> Hi,
>
> I was wondering if the current rmgarch version allows for a VARMA-GARCH modeling.
>
>
> I tried forcing the issue, changing the rmgarch example:
>
>
> uspec.n = multispec(replicate(30, ugarchspec(mean.model = list(armaOrder = c(1,1)))))
> spec.dccn = dccspec(uspec.n, dccOrder = c(1, 1), distribution = 'mvnorm')
> fit.1 = dccfit(spec.dccn, data = X, solver = 'solnp', cluster = cl, fit.control = list(eval.se = FALSE))
>
> but the results were a bit off:
>
>
>> fit.1
>
> *---------------------------------*
> *          DCC GARCH Fit          *
> *---------------------------------*
>
> Distribution         :  mvnorm
> Model                :  DCC(1,1)
> No. Parameters       :  617
> [VAR GARCH DCC UncQ] : [0+180+2+435]
> No. Series           :  30
> No. Obs.             :  1141
> Log-Likelihood       :  70882.93
> Av.Log-Likelihood    :  62.12
>
> Optimal Parameters
> -----------------------------------
>               Estimate  Std. Error  t value Pr(>|t|)
> [AA].mu        0.002643          NA       NA       NA
> [AA].ar1      -0.693738          NA       NA       NA
> [AA].ma1       0.664589          NA       NA       NA
> [AA].omega     0.000065          NA       NA       NA
> [AA].alpha1    0.115044          NA       NA       NA
> [AA].beta1     0.869706          NA       NA       NA
> [AXP].mu       0.002737          NA       NA       NA
> [AXP].ar1      0.072418          NA       NA       NA
> [AXP].ma1     -0.150777          NA       NA       NA
> [AXP].omega    0.000011          NA       NA       NA
> [AXP].alpha1   0.064777          NA       NA       NA
> [AXP].beta1    0.934223          NA       NA       NA
> .
> .
> .
> [Joint]dcca1   0.004960          NA       NA       NA
> [Joint]dccb1   0.942361          NA       NA       NA
>
> Information Criteria
> ---------------------
>
> Akaike       -123.17
> Bayes        -120.44
> Shibata      -123.51
> Hannan-Quinn -122.14
>
>
>
> This seems to be a ARMA-DCC fit, instead of VARMA-DCC and the NA is troubling me.
>
>
>
>
> I understand the package support VAR-Garch. Is there any package currently available in R that have VARMA-Garch model (I don’t have access to RATS)?
>
>
> Any help would be much appreciated,
>
>
>
> Márcio R. Bernardo
> _______________________________________________
> [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.
Reply | Threaded
Open this post in threaded view
|

Re: modeling VARMA-Garch in R

Márcio Rodrigues Bernardo
Thanks for your reply. Alexios

 

I will re-read to your rmgarch documentation to understand how to model VAR-DCC

 

Best regards,



Márcio Bernardo

> Em 25 de jul de 2018, à(s) 22:16, Alexios Galanos <[hidden email]> escreveu:
>
> 1. rmgarch does not support varma, only VAR
> 2. The model you estimated is univariate ARMA(1,1)
> 3. The NAs are because you set fit.control = list(eval.se <http://eval.se/> = FALSE)
> i.e. you are telling the routine to not evaluate the standard errors.
>
> Alexios
>
>
> On Jul 25, 2018, at 16:08, Marcio Bernardo <[hidden email] <mailto:[hidden email]>> wrote:
>
>> Hi,
>>
>> I was wondering if the current rmgarch version allows for a VARMA-GARCH modeling.
>>
>>
>> I tried forcing the issue, changing the rmgarch example:
>>
>>
>> uspec.n = multispec(replicate(30, ugarchspec(mean.model = list(armaOrder = c(1,1)))))
>> spec.dccn = dccspec(uspec.n, dccOrder = c(1, 1), distribution = 'mvnorm')
>> fit.1 = dccfit(spec.dccn, data = X, solver = 'solnp', cluster = cl, fit.control = list(eval.se <http://eval.se/> = FALSE))
>>
>> but the results were a bit off:
>>
>>
>>> fit.1
>>
>> *---------------------------------*
>> *          DCC GARCH Fit          *
>> *---------------------------------*
>>
>> Distribution         :  mvnorm
>> Model                :  DCC(1,1)
>> No. Parameters       :  617
>> [VAR GARCH DCC UncQ] : [0+180+2+435]
>> No. Series           :  30
>> No. Obs.             :  1141
>> Log-Likelihood       :  70882.93
>> Av.Log-Likelihood    :  62.12
>>
>> Optimal Parameters
>> -----------------------------------
>>               Estimate  Std. Error  t value Pr(>|t|)
>> [AA].mu        0.002643          NA       NA       NA
>> [AA].ar1      -0.693738          NA       NA       NA
>> [AA].ma1       0.664589          NA       NA       NA
>> [AA].omega     0.000065          NA       NA       NA
>> [AA].alpha1    0.115044          NA       NA       NA
>> [AA].beta1     0.869706          NA       NA       NA
>> [AXP].mu       0.002737          NA       NA       NA
>> [AXP].ar1      0.072418          NA       NA       NA
>> [AXP].ma1     -0.150777          NA       NA       NA
>> [AXP].omega    0.000011          NA       NA       NA
>> [AXP].alpha1   0.064777          NA       NA       NA
>> [AXP].beta1    0.934223          NA       NA       NA
>> .
>> .
>> .
>> [Joint]dcca1   0.004960          NA       NA       NA
>> [Joint]dccb1   0.942361          NA       NA       NA
>>
>> Information Criteria
>> ---------------------
>>
>> Akaike       -123.17
>> Bayes        -120.44
>> Shibata      -123.51
>> Hannan-Quinn -122.14
>>
>>
>>
>> This seems to be a ARMA-DCC fit, instead of VARMA-DCC and the NA is troubling me.
>>
>>
>>
>>
>> I understand the package support VAR-Garch. Is there any package currently available in R that have VARMA-Garch model (I don’t have access to RATS)?
>>
>>
>> Any help would be much appreciated,
>>
>>
>>
>> Márcio R. Bernardo
>> _______________________________________________
>> [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.