Use this identifier to quote or link this document: http://hdl.handle.net/2072/1885

Accuracy vs. simplicity: a complex trade-off
Aragonès, Enriqueta; Gilboa, Itzhak; Postlewaite, Andrew; Schmeidler, David
Universitat Autònoma de Barcelona. Unitat de Fonaments de l'Anàlisi Econòmica; Institut d'Anàlisi Econòmica
Inductive learning aims at finding general rules that hold true in a database. Targeted learning seeks rules for the predictions of the value of a variable based on the values of others, as in the case of linear or non-parametric regression analysis. Non-targeted learning finds regularities without a specific prediction goal. We model the product of non-targeted learning as rules that state that a certain phenomenon never happens, or that certain conditions necessitate another. For all types of rules, there is a trade-off between the rule's accuracy and its simplicity. Thus rule selection can be viewed as a choice problem, among pairs of degree of accuracy and degree of complexity. However, one cannot in general tell what is the feasible set in the accuracy-complexity space. Formally, we show that finding out whether a point belongs to this set is computationally hard. In particular, in the context of linear regression, finding a small set of variables that obtain a certain value of R2 is computationally hard. Computational complexity may explain why a person is not always aware of rules that, if asked, she would find valid. This, in turn, may explain why one can change other people's minds (opinions, beliefs) without providing new information.
2006-05-09
Anàlisi de regressió
Aquest document està subjecte a una llicència d'ús de Creative Commons, amb la qual es permet copiar, distribuir i comunicar públicament l'obra sempre que se'n citin l'autor original, la universitat, la unitat i l’institut i no se'n faci cap ús comercial ni obra derivada, tal com queda estipulat en la llicència d'ús (http://creativecommons.org/licenses/by-nc-nd/2.5/es/)
Working Paper
Working papers; 564.03
         

Full text files in this document

Files Size Format
56403.pdf 382.0 KB PDF

Show full item record

Related documents

Other documents of the same author

Postlewaite, Andrew; Aragonés, Enriqueta
Aragonès, Enriqueta; Postlewaite, Andrew
 

Coordination

 

Supporters