View Single Post
  #3  
Old 05-20-2014, 03:57 PM
sasin324 sasin324 is offline
Junior Member
 
Join Date: May 2014
Posts: 2
Default Re: overfitting and spurious final hypothesis

Thanks for your response. This is very clear answer for my questions.
However, I still have some confusing about overfitting and the noise.

Suppose I fit the noise in the sample, Does this noise always introduce additional parameters into my model, i.e. the model have unnecessary parameters to overfit the sample?

Is it possible that an additional parameter in a model comes from a spurious relationship (between parameters) that appears only in a sample by chance, e.g. people who born in December have more chance to have cancer, but doesn't appear in out-of-sample data can lead to overfitting phenomenon?

Could feature selection help mitigate overfitting problem?

Best Regards
Reply With Quote