R help - Aug 2011 - Model selection and model efficiency - Search for opinions

Hi,

In order to find the best models I use AIC, more specifically I calculate
Akaike weights then Evidence Ratio (ER) and consider that models with a ER <
2 are equally likely.
But the same problem remain each time I do that. I selected the best models
from a set of them, but I don't know if those models are efficient to
predict (or at least represent) my data.
I can have selected the best element(s) of the list of the worst models.

Do you find it is correct to calculate R2 or pseudo-R2 for the best "set of
models" in order to have an idea of the representativeness of those models
and use this value to select the more efficient model ?

I would be glad to hear your opinions about this !

Thanks,

Arnaud

	[[alternative HTML version deleted]]

1. As this is not really appropriate for R, I suggest replies be private.

2. You might try posting on various statistical forums, e.g. on
http://stats.stackexchange.com/


-- Cheers, Bert

On Wed, Aug 24, 2011 at 12:15 PM, Arnaud Mosnier <a.mosnier at gmail.com>
wrote:
> Hi,
>
> In order to find the best models I use AIC, more specifically I calculate
> Akaike weights then Evidence Ratio (ER) and consider that models with a ER
<
> 2 are equally likely.
> But the same problem remain each time I do that. I selected the best models
> from a set of them, but I don't know if those models are efficient to
> predict (or at least represent) my data.
> I can have selected the best element(s) of the list of the worst models.
>
> Do you find it is correct to calculate R2 or pseudo-R2 for the best
"set of
> models" in order to have an idea of the representativeness of those
models
> and use this value to select the more efficient model ?
>
> I would be glad to hear your opinions about this !
>
> Thanks,
>
> Arnaud
>
> ? ? ? ?[[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> 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.
>