Dear RGrians,
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
Raaed Fadhil Mohammed
the model with least AIC is better model, another way chose stepwise method in GLM to get better model.
0 votes
0 thanks
Ali Hameed Yousif
Check the following link
https://stats.stackexchange.com/questions/9171/aic-or-p-value-which-one-to-choose-for-model-selection
0 votes
0 thanks
Karthikeyan Vasudevan
I agree with Henning Teickner
that backward model selection is probably not the best approach here. Some prior knowledge of the variables would be useful to sift them using some exploratory analysis. The result you have got of competing models that are equally good might be due to strongly several correlated variables. Using model averaging might solve the issue temporarily but the problem might be in the choice of independent variables.
0 votes
0 thanks
- Badges
- Science topic
- Similar topics
- Mathematics
More Mario Garrido's questions See All
Similar questions and discussions