Advanced search
2 files | 619.76 KB Add to list

Immediate prediction under exchangeability and representation insensitivity

Author
Organization
Abstract
We consider immediate predictive inference, where a subject, using a number of observations of a finite number of exchangeable random variables, is asked to coherently model his beliefs about the next observation, in terms of a predictive lower prevision. We study when such predictive lower previsions are representation insensitive, meaning that they are essentially independent of the choice of the (finite) set of possible values for the random variables. Such representation insensitive predictive models have very interesting properties, and among such models, the ones produced by the Imprecise Dirichlet-Multinomial Model are quite special in a number of ways.
Keywords
predictive inference, imprecise Dirichlet-Multinomial model, lower prevision, coherence, representation insensitivity, exchangeability, immediate prediction, representation invariance, Johnson's sufficientness postulate.

Downloads

  • predict-poster.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 136.44 KB
  • Immediate prediction under exchangebaility and representation insensitivity.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 483.33 KB

Citation

Please use this url to cite or link to this publication:

MLA
de Cooman, Gert, et al. “Immediate Prediction under Exchangeability and Representation Insensitivity.” ISIPTA ’07 : Proceedings of the Fifth International Symposium on Imprecise Probability: Theories and Applications, edited by Gert de Cooman et al., Society for Imprecise Probability: Theories and Applications (SIPTA), 2007, pp. 107–16.
APA
de Cooman, G., Miranda, E., & Quaeghebeur, E. (2007). Immediate prediction under exchangeability and representation insensitivity. In G. de Cooman, J. Vejnarová, & M. Zaffalon (Eds.), ISIPTA ’07 : proceedings of the fifth international symposium on imprecise probability: theories and applications (pp. 107–116). Manno, Switzerland: Society for Imprecise Probability: Theories and Applications (SIPTA).
Chicago author-date
Cooman, Gert de, Enrique Miranda, and Erik Quaeghebeur. 2007. “Immediate Prediction under Exchangeability and Representation Insensitivity.” In ISIPTA ’07 : Proceedings of the Fifth International Symposium on Imprecise Probability: Theories and Applications, edited by Gert de Cooman, Jiřina Vejnarová, and Marco Zaffalon, 107–16. Manno, Switzerland: Society for Imprecise Probability: Theories and Applications (SIPTA).
Chicago author-date (all authors)
de Cooman, Gert, Enrique Miranda, and Erik Quaeghebeur. 2007. “Immediate Prediction under Exchangeability and Representation Insensitivity.” In ISIPTA ’07 : Proceedings of the Fifth International Symposium on Imprecise Probability: Theories and Applications, ed by. Gert de Cooman, Jiřina Vejnarová, and Marco Zaffalon, 107–116. Manno, Switzerland: Society for Imprecise Probability: Theories and Applications (SIPTA).
Vancouver
1.
de Cooman G, Miranda E, Quaeghebeur E. Immediate prediction under exchangeability and representation insensitivity. In: de Cooman G, Vejnarová J, Zaffalon M, editors. ISIPTA ’07 : proceedings of the fifth international symposium on imprecise probability: theories and applications. Manno, Switzerland: Society for Imprecise Probability: Theories and Applications (SIPTA); 2007. p. 107–16.
IEEE
[1]
G. de Cooman, E. Miranda, and E. Quaeghebeur, “Immediate prediction under exchangeability and representation insensitivity,” in ISIPTA ’07 : proceedings of the fifth international symposium on imprecise probability: theories and applications, Prague, Czech Republic, 2007, pp. 107–116.
@inproceedings{371965,
  abstract     = {{We consider immediate predictive inference, where a subject, using a number of observations of a finite number of exchangeable random variables, is asked to coherently model his beliefs about the next observation, in terms of a predictive lower prevision. We study when such predictive lower previsions are representation insensitive, meaning that they are essentially independent of the choice of the (finite) set of possible values for the random variables. Such representation insensitive predictive models have very interesting properties, and among such models, the ones produced by the Imprecise Dirichlet-Multinomial Model are quite special in a number of ways.}},
  author       = {{de Cooman, Gert and Miranda, Enrique and Quaeghebeur, Erik}},
  booktitle    = {{ISIPTA '07 : proceedings of the fifth international symposium on imprecise probability: theories and applications}},
  editor       = {{de Cooman, Gert and Vejnarová, Jiřina and Zaffalon, Marco}},
  isbn         = {{9788086742205}},
  keywords     = {{predictive inference,imprecise Dirichlet-Multinomial model,lower prevision,coherence,representation insensitivity,exchangeability,immediate prediction,representation invariance,Johnson's sufficientness postulate.}},
  language     = {{eng}},
  location     = {{Prague, Czech Republic}},
  pages        = {{107--116}},
  publisher    = {{Society for Imprecise Probability: Theories and Applications (SIPTA)}},
  title        = {{Immediate prediction under exchangeability and representation insensitivity}},
  url          = {{http://www.sipta.org/isipta07/proceedings/005.html}},
  year         = {{2007}},
}

Web of Science
Times cited: