[R-SIG-Finance] p-values of garch models

[Patrick Burns]

George Box said:

All models are wrong,
some models are useful.

In particular all garch models are
wrong since markets change over time.
The best you can hope for is a model
that is adequate for your needs.

Looking at p-values won't necessarily
tell you the adequacy of the model for
your application.

Pat


On 12/04/2010 21:38, Konrad Hoppe wrote:
> Hi,
>
> the Ljung Box statistic is valid for differrent models in my case and I want
> to distinguish automatically between those different models. My problem is,
> that it turns out, that there is more than one model with valid box
> statistic, but only one has a residual series which looks like white noise,
> and this model has only significant parameters, while the others have some
> non-significant params. Hence I need to get these p-values from the model
> and I think that there must be possibility since the p-values are
> calculated, but I'm just unable to get them...
> Any ideas to solve that problem?
>
> Konrad Hoppe
>
> -----Ursprüngliche Nachricht-----
> Von: r-sig-finance-bounces at stat.math.ethz.ch
> [mailto:r-sig-finance-bounces at stat.math.ethz.ch] Im Auftrag von Sarbo
> Gesendet: Samstag, 10. April 2010 15:16
> An: r-sig-finance at stat.math.ethz.ch
> Betreff: Re: [R-SIG-Finance] p-values of garch models
>
> What about the Ljung-Box statistics from the GARCH estimation? Wouldn't
> that provide the p-values you're looking for?
>
> On Fri, 2010-04-09 at 23:37 +0200, Konrad Hoppe wrote:
>
>> Hi list,
>>
>> I'm actually trying to model some financial data with use of garch models
>> besides other stuff. But now I'm wondering how to extract the p-values
> from
>> the garch output. I'm just unable to get them. Do I have to calculate them
>> by my own or are there any other possibilities? Of course, I've already
>> checked the help function, but there aren't any advises.
>> Hope you can help me.
>>
>> Thanks in advance,
>> Konrad Hoppe
>> http://www.konrad-hoppe.com/
>>
>>
>> 	[[alternative HTML version deleted]]
>>
>> _______________________________________________
>> R-SIG-Finance at stat.math.ethz.ch 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 stat.math.ethz.ch mailing list
>
> -- 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 stat.math.ethz.ch 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.

-- 
Patrick Burns
patrick at burns-stat.com
http://www.burns-stat.com