Economics at your fingertips  

Prudent case-based prediction when experience is lacking

Patrick H. O'Callaghan

Papers from

Abstract: An inexperienced predictor is asked to qualitatively rank eventualities according to their plausibility, given past cases. Inexperience means that, resampling past cases (with replacement) fails to generate a suitably diverse set of rankings. (4-diversity requires that each of the 4! strict rankings of four eventualities arises for some sample.) Along with other essential consistency requirements, 4-diversity yields a matrix representation that may be viewed as an empirical likelihood function (Gilboa and Schmeidler, 2003). We impose 2-diversity and derive a similar representation: provided the predictor is prudent enough to ensure that the arrival of novel cases will not force her into being dogmatic, intransitive or into revising her existing rankings. We build on this to establish a formal tradeoff between inexperience and the cognitive or computational cost of more abstract resampling.

New Economics Papers: this item is included in nep-evo
Date: 2019-04
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed

Downloads: (external link) Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link:

Access Statistics for this paper

More papers in Papers from
Bibliographic data for series maintained by arXiv administrators ().

Page updated 2019-05-05
Handle: RePEc:arx:papers:1904.02934