I am trying to understand and use the best model selection method for my study. I have inferred models using swarm optimisation methods and used AIC for model selection. On the other hand I am also seeing a lot of references and discussions about BIC as well. Apparently, many papers have tried and concluded to use both AIC and BIC to select the best models. My question here is, What if I use ABC along side with AIC and BIC, how this will effect my study in better way and what would be its pros and corns of using ABC, BIC and AIC as model selection methods ?
Thanks
First let me comment on a couple of things. See the first screenshot for some cautions to doing what you suggested. Now the second attachment shows what we do.. That has worked well for us in our application. Best wishes David Booth
I recommend Sufficient summarized explanation by Professor David Eugene Booth.
Muhammad Usman I think you are mistaken between the Bayesian Information Criteria (BIC) and Approximate Bayesian Computation (ABC; Article Approximation Bayesian Computation
correct me if I am wrong). These two are different things. The BIC is used for "between" model comparison as is the AIC, whereas the ABC is used to estimate parameters.Considering you are using the AIC and made the mistake BIC=ABC, you are likely fitting different IVs into the model and searching for an "optimal solution".
Another reason, I am doubting you use ABC for estimating parameters is that fitting a hierarchical model via ABC is difficult/time consuming (not impossible) as all software I am familiar with uses MCMC as it is better in dealing with multidimensionality. ABC (till now) is very "expensive" for hierarchical models considering the "rejection criterion" and coding (see appendix with 50 lines for ABC and 5 for MCMC).
The AIC:
AIC=2k-2ln(L) [https://en.wikipedia.org/wiki/Akaike_information_criterion]
The BIC:
BIC=ln(n)k-2ln(L) [https://en.wikipedia.org/wiki/Bayesian_information_criterion]
The difference between AIC and BIC is simply (and to shortly) "n".
- Badges
- Science topic
- Similar topics
- Filing