Skip to main content
SpringerLink
Log in

Sets of probability distributions, independence, and convexity

  • Published:
Synthese Aims and scope Submit manuscript

Abstract

This paper analyzes concepts of independence and assumptions of convexity in the theory of sets of probability distributions. The starting point is Kyburg and Pittarelli’s discussion of “convex Bayesianism” (in particular their proposals concerning E-admissibility, independence, and convexity). The paper offers an organized review of the literature on independence for sets of probability distributions; new results on graphoid properties and on the justification of “strong independence” (using exchangeability) are presented. Finally, the connection between Kyburg and Pittarelli’s results and recent developments on the axiomatization of non-binary preferences, and its impact on “complete” independence, are described.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Armstrong T. E. (1989) Countably additive full conditional probabilities. Proceedings of the American Mathematical Society 107(4): 977–987

    Article  Google Scholar 

  • Berger J. O. (1985) Statistical decision theory and Bayesian analysis. Springer, New York

    Google Scholar 

  • Berger J., Moreno E. (1994) Bayesian robustness in bidimensional models: Prior independence. Journal of Statistical Planning and Inference 40: 161–176

    Article  Google Scholar 

  • Bernardo J. M., Smith A. F. M. (1994) Bayesian theory. Wiley, New York

    Book  Google Scholar 

  • Coletti, G., & Scozzafava, R. (2002). Probabilistic logic in a coherent setting. Trends in logic, 15. Dordrecht: Kluwer.

  • Couso, I., Moral, S., & Walley, P. (1999). Examples of independence for imprecise probabilities. In G. de Cooman, F. Cozman, S. Moral, & P. Walley (Eds.), Proceedings of the first international symposium on imprecise probabilities and their applications, Ghent, Belgium (pp. 121–130).

  • Couso I., Moral S., Walley P. (2000) A survey of concepts of independence for imprecise probabilities. Risk, Decision and Policy 5: 165–181

    Article  Google Scholar 

  • Cowell R. G., Dawid A. P., Lauritzen S. L., Spiegelhalter D. J. (1999) Probabilistic networks and expert systems. Springer, New York

    Google Scholar 

  • Cozman F. G. (2000a) Credal networks. Artificial Intelligence 120: 199–233

    Article  Google Scholar 

  • Cozman, F. G. (2000b). Separation properties of sets of probabilities. In C. Boutilier & M. Goldszmidt (Eds.), Conference on uncertainty in artificial intelligence, San Francisco (pp. 107–115).

  • Cozman, F. G. (2001). Constructing sets of probability measures through Kuznetsov’s independence condition. In Proceedings of the second international symposium on imprecise probabilities and their applications, Ithaca, NY, USA (pp. 104–111).

  • Cozman, F. G. (2009). Concentration inequalities and laws of large numbers under epistemic irrelevance. In Proceedings of the sixth international symposium on imprecise probabilities and their applications, Durham, UK.

  • Cozman, F. G., & Seidenfeld, T. (2007). Independence for full conditional measures, graphoids and Bayesian networks. Technical report, PMR, Escola Politecnica, Universidade de Sao Paulo, São Paulo, Brazil.

  • Cozman F. G., Walley P. (2005) Graphoid properties of epistemic irrelevance and independence. Annals of Mathematics and Artificial Intelligence 45: 173–195

    Article  Google Scholar 

  • Dawid A. P. (1979) Conditional independence in statistical theory (with discussion). Journal of the Royal Statistical Society B 41: 1–31

    Google Scholar 

  • Dawid A. P. (2001) Separoids: A mathematical framework for conditional independence and irrelevance. Annals of Mathematics and Artificial Intelligence 32(1–4): 335–372

    Article  Google Scholar 

  • de Campos, C. P., & Cozman, F. G. (2004). Inference in credal networks using multilinear programming. In E. Onaindia & S. Staab (Eds.), Proceedings of the second starting AI researchers’ symposium (STAIRS), Amsterdam, The Netherlands (pp. 50–61).

  • de Campos, C. P., & Cozman, F. G. (2005). The inferential complexity of Bayesian and credal networks. In International joint conference on artificial intelligence (IJCAI), Edinburgh, UK (pp. 1313–1318).

  • de Campos C. P., Cozman F. G. (2007) Computing lower and upper expectations under epistemic independence. International Journal of Approximate Reasoning 44(3): 244–260

    Article  Google Scholar 

  • de Campos, L., & Moral, S. (1995). Independence concepts for convex sets of probabilities. In P. Besnard & S. Hanks (Eds.), XI conference on uncertainty in artificial intelligence, San Francisco, CA, USA (pp. 108–115).

  • de Cooman G., Miranda E. (2008) Weak and strong laws of large numbers for coherent lower previsions. Journal of Statistical Planning and Inference 138(8): 2409–2432

    Article  Google Scholar 

  • de Finetti, B. (1974). Theory of probability (Vols. 1–2). New York: Wiley.

  • Diaconis P., Freedman D. (1980) de Finetti’s theorem for Markov chains. The Annals of Probability 8(1): 115–130

    Article  Google Scholar 

  • Diaconis P., Zabell S. L. (1982) Updating subjective probability. Journal of the American Statistical Association 77(380): 822–829

    Google Scholar 

  • Dubins L. E. (1975) Finitely additive conditional probability, conglomerability and disintegrations. Annals of Statistics 3(1): 89–99

    Google Scholar 

  • Fagiuoli E., Zaffalon M. (1998) 2U: An exact interval propagation algorithm for polytrees with binary variables. Artificial Intelligence 106(1): 77–107

    Article  Google Scholar 

  • Fishburn P. C. (1970) Utility theory for decision making. Wiley, New York

    Google Scholar 

  • Gardenfors P., Sahlin N. E. (1982) Unreliable probabilities, risk taking and decision making. Synthese 53: 361–386

    Article  Google Scholar 

  • Geiger D., Verma T., Pearl J. (1990) d-Separation: From theorems to algorithms. Uncertainty in Artificial Intelligence 5: 139–148

    Google Scholar 

  • Giron F. J., Rios S. (1980) Quasi-Bayesian behaviour: A more realistic approach to decision making?. In: Bernardo J. M., DeGroot J. H., Lindley D. V., Smith A. F. M. (eds) Bayesian statistics. University Press, Valencia, pp 17–38

    Google Scholar 

  • Hajek A. (2003) What conditional probability could not be. Synthese 137: 273–323

    Article  Google Scholar 

  • Halpern, J. Y. (2001). Lexicographic probability, conditional probability, and nonstandard probability. In Proceedings of the eighth conference on theoretical aspects of rationality and knowledge (pp. 17–30).

  • Hammond P. J. (1994) Elementary non-Archimedean representations of probability for decision theory and games. In: Humphreys P. (ed.) Patrick suppes: Scientific philosopher (Vol. 1). Kluwer, Dordrecht, pp 25–59

    Chapter  Google Scholar 

  • Heath D., Sudderth W. (1976) de Finetti’s theorem on exchangeable variables. The American Statistician 30(4): 188–189

    Google Scholar 

  • Jeffrey R. (1965) The logic of decision. McGraw-Hill, New York

    Google Scholar 

  • Kadane, J. B., Schervish, M. J., & Seidenfeld, T. (2004). A Rubinesque theory of decision. In A festschrift for Herman Rubin (pp. 45–55). Beachwood, OH: Institute of Mathematical Statistics.

  • Keynes J. M. (1921) A treatise on probability. Macmillan and Co, London

    Google Scholar 

  • Kikuti, D., Cozman, F. G., & de Campos, C. P. (2005). Partially ordered preferences in decision trees: Computing strategies with imprecision in probabilities. In IJCAI workshop on advances in preference handling, Edinburgh, UK (pp. 118–123).

  • Krauss P. (1968) Representation of conditional probability measures on Boolean algebras. Acta Mathematica Academiae Scientiarum Hungaricae 19(3–4): 229–241

    Article  Google Scholar 

  • Kuznetsov, V. P. (1991). Interval statistical methods. Radio i Svyaz Publ (in Russian).

  • Kuznetsov, V. P. (1995). Auxiliary problems of statistical data processing: Interval approach. In Extended abstracts of APIC95: International workshop on applications of interval computations (pp. 123–129).

  • Kyburg, Jr., H., & Pittarelli, M. (1992a). Some problems for convex Bayesians. In Conference on uncertainty in artificial intelligence (pp. 149–154).

  • Kyburg, Jr., H. E., & Pittarelli, M. (1992b). Set-based Bayesianism. technical report UR CSD; TR 407. University of Rochester, Computer Science Department. http://hdl.handle.net/1802/765.

  • Kyburg H. E., Pittarelli M. (1996) Set-based Bayesianism. IEEE Transactions on Systems, Man and Cybernetics A 26(3): 324–339

    Article  Google Scholar 

  • Lad F. (1996) Operational subjective statistical methods: A mathematical, philosophical, and historical, and introduction. Wiley, New York

    Google Scholar 

  • Levi I. (1980) The enterprise of knowledge. MIT Press, Cambridge, MA

    Google Scholar 

  • Moral S. (2005) Epistemic irrelevance on sets of desirable gambles. Annals of Mathematics and Artificial Intelligence 45(1–2): 197–214

    Article  Google Scholar 

  • Moral S., Cano A. (2002) Strong conditional independence for credal sets. Annals of Mathematics and Artificial Intelligence 35: 295–321

    Article  Google Scholar 

  • Pearl J. (1988) Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann, San Mateo, CA

    Google Scholar 

  • Schervish M. J. (1995) Theory of statistics. Springer, New York

    Book  Google Scholar 

  • Schervish, M., Seidenfeld, T., Kadane, J., & Levi, I. (2003). Extensions of expected utility theory and some limitations of pairwise comparisons. In J.-M. Bernard, T. Seidenfeld, & M. Zaffalon (Eds.), Proceedings of the third international symposium on imprecise probabilities and their applications (pp. 496–510).

  • Seidenfeld, T. (2001). Remarks on the theory of conditional probability: Some issues of finite versus countable additivity. In Statistics–philosophy, recent history, and relations to science (pp. 167–177). Dordrecht: Kluwer.

  • Seidenfeld, T. (2007). Conditional independence, imprecise probabilities, null-events and graph-theoretic models. Seimour Geisser Distinguished Lecture, School of Statistics, University of Minnesota, Minneapolis, MN.

  • Seidenfeld T., Schervish M. J., Kadane J. B. (1990) Decisions without ordering. In: Sieg W. (eds) Acting and reflecting. Kluwer, Dordrecht, pp 143–170

    Chapter  Google Scholar 

  • Seidenfeld T., Schervish M. J., Kadane J. B. (2001) Improper regular conditional distributions. The Annals of Probability 29(4): 1612–1624

    Article  Google Scholar 

  • Seidenfeld, T., Schervish, M., & Kadane, J. (2007). Coherent choice functions under uncertainty. In International symposium on imprecise probability: Theories and applications, Prague, Czech Republic.

  • Sen A. (1977) Social choice theory: A reexamination. Econometrica 45: 53–89

    Article  Google Scholar 

  • Shafer G. (1976) A mathematical theory of evidence. Princeton University Press, Princeton, NJ

    Google Scholar 

  • Smith C. A. B. (1961) Consistency in statistical inference and decision. Journal Royal Statistical Society B 23: 1–25

    Google Scholar 

  • Troffaes M. (2004) Decision making with imprecise probabilities: A short review. SIPTA Newsletter 2: 4–7

    Google Scholar 

  • Utkin, L. V., & Augustin, T. (2005). Powerful algorithms for decision making under prior information and general ambiguity attitudes. In Proceedings of the fourth international symposium on imprecise probabilities and their applications (pp. 349–358).

  • Vantaggi, B. (2001). Graphical models for conditional independence structures. In Second international symposium on imprecise probabilities and their applications (pp. 332–341).

  • Walley, P. (1982). The elicitation and aggregation of beliefs. Technical report 23, Department of Statistics, University of Warwick, Warwick, UK

  • Walley P. (1991) Statistical reasoning with imprecise probabilities. Chapman and Hall, London

    Google Scholar 

  • Walley P., Fine T. L. (1982) Towards a frequentist theory of upper and lower probability. Annals of Statistics 10(3): 741–761

    Article  Google Scholar 

  • Weichselberger K. (2000) The theory of interval-probability as a unifying concept for uncertainty. International Journal of Approximate Reasoning 24(2–3): 149–170

    Article  Google Scholar 

  • Weichselberger, K., Augustin, T., & Wallner, A. (2001). Elementare Grundbegriffe einer allgemeineren Wahrscheinlichkeitsrechnung I: Intervallwahrscheinlichkeit als umfassendes Konzept. Heidelberg: Physica-Verlag.

  • Williams, P. M. (1975). Coherence, strict coherence and zero probabilities. In Fifth international congress in logic, methodology and philosophy of science (Vol. VI, pp. 29–30).

  • Williams P. M. (2007) Notes on conditional previsions. International Journal of Approximate Reasoning 44: 366–383

    Article  Google Scholar 

  • Yaghlane B. B., Smets P., Mellouli K. (2002a) Belief function independence: I. The marginal case. International Journal of Approximate Reasoning 29(1): 47–70

    Article  Google Scholar 

  • Yaghlane B. B., Smets P., Mellouli K. (2002b) Belief function independence: II. The conditional case. International Journal of Approximate Reasoning 31(1–2): 31–75

    Article  Google Scholar 

  • Zaman A. (1986) A finite form of de Finetti’s theorem for stationary Markov exchangeability. The Annals of Probability 14(4): 1418–1427

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Escola Politécnica, Universidade de São Paulo, São Paulo, SP, Brazil

    Fabio G. Cozman

Authors
  1. Fabio G. Cozman
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Fabio G. Cozman.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cozman, F.G. Sets of probability distributions, independence, and convexity. Synthese 186, 577–600 (2012). https://doi.org/10.1007/s11229-011-9999-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11229-011-9999-0

Keywords

Search

Navigation