[R-sig-ME] AIC and other IT indexes criteria for for backward, forward and stepwise regression
bbo|ker @end|ng |rom gm@||@com
Wed Dec 18 21:44:03 CET 2019
This is a reasonable question, but it isn't at all specific to mixed
models (which is the topic of this mailing list). You could try
I'm sure opinions differ a lot, and answers will almost certainly
depend on your goals and context, but *if* I were going to do model
selection (which I think is very often a bad idea!) I would simply pick
the model with the minimum AIC, which will (asymptotically) have the
smallest expected Kullback-Leibler distance.
On 2019-12-18 6:07 a.m., Mario Garrido wrote:
> Dear users,
> Im currently exploring on the use of AIC and other I-T indexes criteria for
> backward, forward and stepwise regression.
> Usually, when applying IT indexes for Multimodal Inference, we choose a set
> of 'good models' depending on different criteria, but mainly, all models
> with delta AIC<2, and then we averaged the estimates between the set of
> models or make conclusions based on the set of models, no need to average.
> However, if Im not wrong, the goal of backward etc is to get to one 'best'
> final model. I understand the use of AIC in this framework but, is there
> any criteria to select the best model in this case? Do I simply have to
> choose the model with the lowest AIC no matter whether there is another
> model whose delta is less than 2? Does it depend on a personal criteria?
> For example, if my 'maximal' or saturated model has the lowest AIC and the
> model dropping one variable has a delta of 0.5, which model to choose?
> I was looking on the web and I have found no answer to this. So, any
> literature recommendation or advice will be welcome.
More information about the R-sig-mixed-models