| 
  • If you are citizen of an European Union member nation, you may not use this service unless you are at least 16 years old.

  • Stop wasting time looking for files and revisions! Dokkio, a new product from the PBworks team, integrates and organizes your Drive, Dropbox, Box, Slack and Gmail files. Sign up for free.

View
 

AkaikeInfoCriterion

Page history last edited by mike@mbowles.com 8 years, 5 months ago

The class asked for more detail on using AIC to evaluate clustering solutions.  Here are a couple of references that we'll cover regarding AIC. 

 

Here are lecture notes from a class at Univ of Iowa.  We'll follow this derivation. 

ms_lec_2_ho.pdf

 

Here's a short paper that describes a correction to AIC when the data set is small.

aic_reg.pdf

 

This paper is as close as I could get to Akaike's original paper describing the technique.

10.1.1.55.7181.pdf

 

Here's a relatively recent survey-ish sort of paper with good references for those who need more.  This paper also has comparison with BIC (Bayesian Information Criterion)

Burnham_and_Anderson_2004_Multimodel_Inference.pdf

 

This paper does a comparison of AIC with BIC in the context of mixed model regression. 

BestRegression.doc

Comments (0)

You don't have permission to comment on this page.