Calculating AIC and BIC for Time Series Models

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

Calculating AIC and BIC for Time Series Models

PaulJr
Dear friends,

I have been fitting some TS models from the forecast package like ets(),
ses(), hw(), HoltWinters(), stlf(), bats() and tbats(), however, when
trying to use the AIC and BIC functions, I receive the following error
message:

Error in UseMethod("logLik") :
  no applicable method for 'logLik' applied to an object of class "forecast"

Yes, the message is clear, those functions cannot be applied to objects
from the forecast class. However, I would like to know if there is a way to
assess the goodness of fit for this models that is somewhat equivalent to
AIC and BIC, or of there is any other function that could help me in the
model selection stage, other than computing MASE, MAPE, etc.

Any help and or guidance will be greatly appreciated.

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Calculating AIC and BIC for Time Series Models

David Winsemius

> On Jun 8, 2018, at 12:26 PM, Paul Bernal <[hidden email]> wrote:
>
> Dear friends,
>
> I have been fitting some TS models from the forecast package like ets(),
> ses(), hw(), HoltWinters(), stlf(), bats() and tbats(), however, when
> trying to use the AIC and BIC functions, I receive the following error
> message:
>
> Error in UseMethod("logLik") :
>  no applicable method for 'logLik' applied to an object of class "forecast"
>
> Yes, the message is clear, those functions cannot be applied to objects
> from the forecast class. However, I would like to know if there is a way to
> assess the goodness of fit for this models that is somewhat equivalent to
> AIC and BIC, or of there is any other function that could help me in the
> model selection stage, other than computing MASE, MAPE, etc.
>
> Any help and or guidance will be greatly appreciated.
>
> [[alternative HTML version deleted]]

Fourth google hit on a search "goodness of fit measures for forecasts" by the author of hte forecast package:

goodness of fit measures for forecasts


>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius
Alameda, CA, USA

'Any technology distinguishable from magic is insufficiently advanced.'   -Gehm's Corollary to Clarke's Third Law

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Calculating AIC and BIC for Time Series Models

David Winsemius

> On Jun 8, 2018, at 12:43 PM, David Winsemius <[hidden email]> wrote:
>
>
>> On Jun 8, 2018, at 12:26 PM, Paul Bernal <[hidden email]> wrote:
>>
>> Dear friends,
>>
>> I have been fitting some TS models from the forecast package like ets(),
>> ses(), hw(), HoltWinters(), stlf(), bats() and tbats(), however, when
>> trying to use the AIC and BIC functions, I receive the following error
>> message:
>>
>> Error in UseMethod("logLik") :
>> no applicable method for 'logLik' applied to an object of class "forecast"
>>
>> Yes, the message is clear, those functions cannot be applied to objects
>> from the forecast class. However, I would like to know if there is a way to
>> assess the goodness of fit for this models that is somewhat equivalent to
>> AIC and BIC, or of there is any other function that could help me in the
>> model selection stage, other than computing MASE, MAPE, etc.
>>
>> Any help and or guidance will be greatly appreciated.
>>
>> [[alternative HTML version deleted]]
>
> Fourth google hit on a search "goodness of fit measures for forecasts" by the author of hte forecast package:

https://pdfs.semanticscholar.org/af71/3d815a7caba8dff7248ecea05a5956b2a487.pdf

>
>>
>> ______________________________________________
>> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
>> https://stat.ethz.ch/mailman/listinfo/r-help
>> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
>> and provide commented, minimal, self-contained, reproducible code.
>
> David Winsemius
> Alameda, CA, USA
>
> 'Any technology distinguishable from magic is insufficiently advanced.'   -Gehm's Corollary to Clarke's Third Law
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

David Winsemius
Alameda, CA, USA

'Any technology distinguishable from magic is insufficiently advanced.'   -Gehm's Corollary to Clarke's Third Law

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
Reply | Threaded
Open this post in threaded view
|

Re: Calculating AIC and BIC for Time Series Models

Bert Gunter-2
... Or have you looked here?

https://cran.r-project.org/web/views/TimeSeries.html

Bert

On Fri, Jun 8, 2018, 1:29 PM David Winsemius <[hidden email]> wrote:

>
> > On Jun 8, 2018, at 12:43 PM, David Winsemius <[hidden email]>
> wrote:
> >
> >
> >> On Jun 8, 2018, at 12:26 PM, Paul Bernal <[hidden email]>
> wrote:
> >>
> >> Dear friends,
> >>
> >> I have been fitting some TS models from the forecast package like ets(),
> >> ses(), hw(), HoltWinters(), stlf(), bats() and tbats(), however, when
> >> trying to use the AIC and BIC functions, I receive the following error
> >> message:
> >>
> >> Error in UseMethod("logLik") :
> >> no applicable method for 'logLik' applied to an object of class
> "forecast"
> >>
> >> Yes, the message is clear, those functions cannot be applied to objects
> >> from the forecast class. However, I would like to know if there is a
> way to
> >> assess the goodness of fit for this models that is somewhat equivalent
> to
> >> AIC and BIC, or of there is any other function that could help me in the
> >> model selection stage, other than computing MASE, MAPE, etc.
> >>
> >> Any help and or guidance will be greatly appreciated.
> >>
> >>      [[alternative HTML version deleted]]
> >
> > Fourth google hit on a search "goodness of fit measures for forecasts"
> by the author of hte forecast package:
>
>
> https://pdfs.semanticscholar.org/af71/3d815a7caba8dff7248ecea05a5956b2a487.pdf
>
> >
> >>
> >> ______________________________________________
> >> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> >> https://stat.ethz.ch/mailman/listinfo/r-help
> >> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> >> and provide commented, minimal, self-contained, reproducible code.
> >
> > David Winsemius
> > Alameda, CA, USA
> >
> > 'Any technology distinguishable from magic is insufficiently advanced.'
>  -Gehm's Corollary to Clarke's Third Law
> >
> > ______________________________________________
> > [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> > https://stat.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> > and provide commented, minimal, self-contained, reproducible code.
>
> David Winsemius
> Alameda, CA, USA
>
> 'Any technology distinguishable from magic is insufficiently advanced.'
>  -Gehm's Corollary to Clarke's Third Law
>
> ______________________________________________
> [hidden email] mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>

        [[alternative HTML version deleted]]

______________________________________________
[hidden email] mailing list -- To UNSUBSCRIBE and more, see
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.