|
 
|
[SAP07a] Model Selection and Predictive Inference
Conférence Internationale avec comité de lecture : Trends and Challenges in Applied Mathematics, Bucarest, January 2007, pp.92-96,
motcle:
Résumé:
Methods based on penalized likelihood cannot be applied in many problems. Statistical learning theory provide the theoretical framework for predictive inference, but model choice based on VC dimension is often not feasible. In binary classification, ROC curve and AUC provide a reasonable criterium for model choice, combined with resampling.
BibTeX
| @inproceedings { | |||
| SAP07a, | |||
| title | = | "{Model Selection and Predictive Inference}", | |
| author | = | " G. Saporta ", | |
| booktitle | = | "{Trends and Challenges in Applied Mathematics, Bucarest}", | |
| year | = | 2007, | |
| month | = | "January", | |
| pages | = | "92-96", | |
| } | |||
