# Probabilistic Opinion Pooling with Imprecise Probabilities

- 678 Downloads
- 1 Citations

## Abstract

The question of how the probabilistic opinions of different individuals should be aggregated to form a group opinion is controversial. But one assumption seems to be pretty much common ground: for a group of Bayesians, the representation of group opinion should itself be a unique probability distribution (Madansky [44]; Lehrer and Wagner [34]; McConway *Journal of the American Statistical Association, 76*(374), 410–414, [45]; Bordley *Management Science*, 28(10), 1137–1148, [5]; Genest et al. *The Annals of Statistics*, 487–501, [21]; Genest and Zidek *Statistical Science*, 114–135, [23]; Mongin *Journal of Economic Theory, 66*(2), 313–351, [46]; Clemen and Winkler *Risk Analysis, 19*(2), 187–203, [7]; Dietrich and List [14]; Herzberg *Theory and Decision*, 1–19, [28]). We argue that this assumption is not always in order. We show how to extend the canonical mathematical framework for pooling to cover pooling with *imprecise probabilities* (IP) by employing *set-valued* pooling functions and generalizing common pooling axioms accordingly. As a proof of concept, we then show that one IP construction satisfies a number of central pooling axioms that are not jointly satisfied by any of the standard pooling recipes on pain of triviality. Following Levi (*Synthese, 62*(1), 3–11, [39]), we also argue that IP models admit of a much better philosophical motivation as a model of rational consensus.

## Keywords

Aggregation Consensus Imprecise probabilities Pooling Social epistemology## Notes

### Acknowledgments

Several people gave us very helpful feedback on the ideas in this paper. Thanks to Robby Finley and Yang Liu for their comments on a presentation given to the Formal Philosophy reading group at Columbia University, and to members of the audiences at the Columbia Graduate Student Workshop, the Probability and Belief Workshop organized by Hans Rott at the University of Regensburg, and a presentation at CUNY organized by Rohit Parikh. We are grateful to Arthur Heller, Michael Nielsen, Teddy Seidenfeld, Reuben Stern, and Mark Swails for their excellent comments on drafts of the paper. We would like to especially thank Isaac Levi for extensive discussion of the content of this paper and comments on drafts and a presentation. Finally, thanks to both the editor and the anonymous referee. The referee provided engaged and thorough feedback that has undoubtedly improved the essay in a number of ways.

## References

- 1.Aczél, J. (1948). On mean values.
*Bulletin of the American Mathematical Society*,*54*(4), 392–400.CrossRefGoogle Scholar - 2.Aczél, J., & Oser, H. (2006).
*Lectures on functional equations and their applications*. Courier Corporation.Google Scholar - 3.Arló-Costa, H., & Helzner, J. (2010). Ambiguity aversion: the explanatory power of indeterminate probabilities.
*Synthese*,*172*(1), 37–55.CrossRefGoogle Scholar - 4.Bacharach, M. (1972). Scientific disagreement. Unpublished manuscript.Google Scholar
- 5.Bordley, R.F. (1982). A multiplicative formula for aggregating probability assessments.
*Management Science*,*28*(10), 1137–1148.CrossRefGoogle Scholar - 6.Bradley, S. (2014). Imprecise probabilities, In Zalta, E.N. (Ed.),
*The Stanford Encyclopedia of Philosophy (Winter 2014 ed.)*Google Scholar - 7.Clemen, R.T., & Winkler, R.L. (1999). Combining probability distributions from experts in risk analysis.
*Risk Analysis*,*19*(2), 187–203.Google Scholar - 8.Cozman, F. (1998). Irrelevance and independence relations in quasi-bayesian networks,
*Proceedings of the fourteenth conference on uncertainty in artificial intelligence*. Morgan Kaufmann Publishers Inc (pp. 89–96).Google Scholar - 9.Cozman, F.G. (2000). Credal networks.
*Artificial Intelligence*,*120*(2), 199–233.CrossRefGoogle Scholar - 10.de Campos, L.M., & Moral, S. (1995). Independence concepts for convex sets of probabilities,
*Proceedings of the eleventh conference on uncertainty in artificial intelligence*. Morgan Kaufmann Publishers Inc. (pp. 108–115).Google Scholar - 11.de Finetti, B. (1931). Sul concetto di media.
*Giornale dell’Istituto Italiano degli Attuari*,*2*, 369– 396.Google Scholar - 12.de Finetti, B. (1964). Foresight: its logical laws, its subjective sources, In Kyburg, H.E., & Smoklery, H.E. (Eds.)
*Studies in Subjective Probability*. Wiley.Google Scholar - 13.Dietrich, F. (2010). Bayesian group belief.
*Social Choice and Welfare*,*35*(4), 595–626.CrossRefGoogle Scholar - 14.Dietrich, F., & List, C. (2014). Probabilistic opinion pooling. In Hájek, A., & Hitchcock, C. (Eds.),
*Oxford Handbook of Probability and Philosophy*. Oxford University Press.Google Scholar - 15.Ellsberg, D. (1963). Risk, ambiguity, and the savage axioms.
*The Quarterly Journal of Economics*,*77*(2), 327–336.CrossRefGoogle Scholar - 16.French, S. (1985). Group consensus probability distributions: a critical survey. In Bernardo, D.L.J.M., DeGroot, M.H., & Smith, A. (Eds.),
*Bayesian statistics: proceedings of the second valencia international meeting*. North-Holland, (Vol. 2 pp. 183–201).Google Scholar - 17.Gaifman, H., & Snir, M. (1982). Probabilities over rich languages, testing and randomness.
*The Journal Of Symbolic Logic*,*47*(03), 495–548.CrossRefGoogle Scholar - 18.Gärdenfors, P., & Rott, H. (1995).
*Handbook of logic in artificial intelligence and logic programming: epistemic and temporal reasoning*Vol. 4. Oxford: Oxford University Press. Chapter Belief Revision.Google Scholar - 19.Gärdenfors, P., & Sahlin, N.-E. (1982). Unreliable probabilities, risk taking, and decision making.
*Synthese*,*53*(3), 361–386.CrossRefGoogle Scholar - 20.Genest, C. (1984). A characterization theorem for externally bayesian groups. The Annals of Statistics.Google Scholar
- 21.Genest, C., McConway, K.J., & Schervish, M.J. (1986). Characterization of externally Bayesian pooling operators. The Annals of Statistics.Google Scholar
- 22.Genest, C., & Wagner, C.G. (1987). Further evidence against independence preservation in expert judgement synthesis.
*Aequationes Mathematicae*,*32*(1), 74–86.CrossRefGoogle Scholar - 23.Genest, C., & Zidek, J.V. (1986). Combining probability distributions: a critique and an annotated bibliography. Statistical Science.Google Scholar
- 24.Gilboa, I., & Schmeidler, D. (1989). Maxmin expected utility with non-unique prior.
*Journal of Mathematical Economics*,*18*(2), 141–153.CrossRefGoogle Scholar - 25.Girón, F.J., & Ríos, S. (1980). Quasi-bayesian behaviour: a more realistic approach to decision making?
*Trabajos de Estadý de Investigació,n Operativa*,*31*(1), 17–38.CrossRefGoogle Scholar - 26.Halmos, P.R. (1963).
*Lectures on boolean algebras*. Princeton: Van Nostrand.Google Scholar - 27.Herron, T., Seidenfeld, T., & Wasserman, L. (1997). Divisive conditioning: further results on dilation. Philosophy of Science.Google Scholar
- 28.Herzberg, F. (2014). Aggregating infinitely many probability measures. Theory and Decision.Google Scholar
- 29.Kaplan, M. (1996).
*Decision theory as philosophy*. Cambridge: Cambridge University Press.CrossRefGoogle Scholar - 30.Kolmogorov, A.N. (1930). Sur la notion de la moyenne.
*Atti della R. Academia Nazionale dei Lincei*,*12*(9), 388–391.Google Scholar - 31.Kyburg, H.E. (1998). Interval-valued probabilities. Imprecise Probabilities Project.Google Scholar
- 32.Kyburg, H.E., & Pittarelli, M. (1992). Some problems for convex bayesians,
*Proceedings of the eighth international conference on uncertainty in artificial intelligence*. Morgan Kaufmann Publishers Inc. (pp. 149–154).CrossRefGoogle Scholar - 33.Kyburg, H.E., & Pittarelli, M. (1996). Set-based Bayesianism.
*IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans*,*26*(3), 324–339.CrossRefGoogle Scholar - 34.Lehrer, K., & Wagner, C. (1981).
*Rational consensus in science and society: a philosophical and mathematical study*Vol. 21. Springer.Google Scholar - 35.Lehrer, K., & Wagner, C. (1983). Probability amalgamation and the independence issue: a reply to laddaga.
*Synthese*,*55*(3), 339–346.CrossRefGoogle Scholar - 36.Levi, I. (1974). On indeterminate probabilities.
*The Journal of Philosophy*,*71*(13), 391–418.CrossRefGoogle Scholar - 37.Levi, I. (1978). Irrelevance,
*Foundations and applications of decision theory*. Springer (pp. 263–273).Google Scholar - 38.Levi, I. (1980).
*The enterprise of knowledge*. Cambridge: MIT Press.Google Scholar - 39.Levi, I. (1985). Consensus as shared agreement and outcome of inquiry.
*Synthese*,*62*(1), 3–11.CrossRefGoogle Scholar - 40.Levi, I. (1986a).
*Hard choices: Decision making under unresolved conflict*. Cambridge: Cambridge University Press.CrossRefGoogle Scholar - 41.Levi, I. (1986b). The paradoxes of allais and ellsberg.
*Economics and Philosophy*,*2*(1), 23–53.CrossRefGoogle Scholar - 42.Levi, I. (1990). Pareto unanimity and consensus.
*The Journal of Philosophy*,*87*(9), 481–492.CrossRefGoogle Scholar - 43.Levi, I. (2009). Why indeterminate probability is rational.
*Journal of Applied Logic*,*7*(4), 364–376.CrossRefGoogle Scholar - 44.Madansky, A. (1964). Externally Bayesian Groups. Santa Monica, CA: RAND Corporation . http://www.rand.org/pubs/research_memoranda/RM4141.html. Also available in print form.
- 45.McConway, K.J. (1981). Marginalization and linear opinion pools.
*Journal of the American Statistical Association*,*76*(374), 410–414.CrossRefGoogle Scholar - 46.Mongin, P. (1995). Consistent bayesian aggregation.
*Journal of Economic Theory*,*66*(2), 313–351.CrossRefGoogle Scholar - 47.Moral, S., & Del Sagrado, J. (1998). Aggregation of imprecise probabilities, In Bouchon-Meunier, B. (Ed.),
*Aggregation and fusion of imperfect information*. Springer (pp. 162–188).CrossRefGoogle Scholar - 48.Nau, R.F. (2002). The aggregation of imprecise probabilities.
*Journal of Statistical Planning and Inference*,*105*(1), 265–282.CrossRefGoogle Scholar - 49.Ouchi, F. (2004). A literature review on the use of expert opinion in probabilistic risk analysis. Washington, DC: World Bank.Google Scholar
- 50.Pedersen, A.P., & Wheeler, G. (2014). Demystifying dilation.
*Erkenntnis*,*79*(6), 1305–1342.CrossRefGoogle Scholar - 51.Pedersen, A.P., & Wheeler, G. (2015). Dilation, disintegrations, and delayed decisions,
*Proceedings of the 9th*.Google Scholar - 52.Ramsey, F.P. (1931). Truth and probability. The Foundations of Mathematics and Other Logical Essays.Google Scholar
- 53.Rockafellar, R.T. (1970).
*Convex analysis. Number 28*. Princeton: Princeton University Press.CrossRefGoogle Scholar - 54.Savage, L. (1972 Originally published in 1954).
*The foundations of statistics*. New York: Wiley.Google Scholar - 55.Seidenfeld, T. (1993). Outline of a theory of partially ordered preferences.
*Philosophical Topics*,*21*(1), 173–189.CrossRefGoogle Scholar - 56.Seidenfeld, T., Kadane, J.B., & Schervish, M.J. (1989). On the shared preferences of two bayesian decision makers.
*The Journal of Philosophy*,*86*(5), 225–244.CrossRefGoogle Scholar - 57.Seidenfeld, T., Schervish, M.J., & Kadane, J.B. (2010). Coherent choice functions under uncertainty.
*Synthese*,*172*(1), 157–176.CrossRefGoogle Scholar - 58.Seidenfeld, T., & Wasserman, L. (1993). Dilation for sets of probabilities.
*The Annals of Statistics*,*21*(3), 1139–1154.CrossRefGoogle Scholar - 59.Smith, C.A.B. (1961). Consistency in statistical inference and decision.
*Journal of the Royal Statistical Society. Series B (Methodological)*,*23*(1), 1–37.Google Scholar - 60.Stewart, R.T., & Ojea Quintana, I. (MS2). Learning and pooling, pooling and learning. Unpublished manuscript.Google Scholar
- 61.Stone, M. (1961). The opinion pool.
*The Annals of Mathematical Statistics*,*32*(4), 1339–1342.CrossRefGoogle Scholar - 62.Wagner, C. (2009). Jeffrey conditioning and external bayesianity.
*Logic Journal of IGPL*,*18*(2), 336–345.CrossRefGoogle Scholar - 63.Walley, P. (1982). The elicitation and aggregation of beliefs. Technical report 23, Department of Statistics, University of Warwick, Coventry CV4 7AL, England.Google Scholar
- 64.Walley, P. (1991).
*Statistical reasoning with imprecise probabilities*. London: Chapman and Hall.CrossRefGoogle Scholar - 65.Wasserman, L. (1993). Review: statistical reasoning with imprecise probabilities by Peter Walley.
*Journal of the American Statistical Association*,*88*(422), 700–702.CrossRefGoogle Scholar - 66.Wasserman, L., & Seidenfeld, T. (1994). The dilation phenomenon in robust bayesian inference.
*Journal of Statistical Planning and Inference*,*40*(2), 345–356.CrossRefGoogle Scholar