Skip to main content
Log in

Merging of opinions in game-theoretic probability

  • Published:
Annals of the Institute of Statistical Mathematics Aims and scope Submit manuscript

Abstract

This paper gives game-theoretic versions of several results on “merging of opinions” obtained in measure-theoretic probability and algorithmic randomness theory. An advantage of the game-theoretic versions over the measure-theoretic results is that they are pointwise, their advantage over the algorithmic randomness results is that they are non-asymptotic, but the most important advantage over both is that they are very constructive, giving explicit and efficient strategies for players in a game of prediction.

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

Access this article

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

Instant access to the full article PDF.

Similar content being viewed by others

References

  • Amari, S., Nagaoka, H. (2000). Methods of information geometry. Providence, RI: American Mathematical Society. Japanese original (1993): Tokyo: Iwanami Shoten.

  • Blackwell D., Dubins L. (1962). Merging of opinions with increasing information. Annals of Mathematical Statistics 33, 882–886

    Article  MATH  MathSciNet  Google Scholar 

  • Dawid A.P. (1984). Statistical theory: the prequential approach. Journal of the Royal Statistical Society A 147, 278–292

    Article  MATH  MathSciNet  Google Scholar 

  • Dawid A.P. (1985). Calibration-based empirical probability (with discussion). Annals of Statistics 13, 1251–1285

    Article  MATH  MathSciNet  Google Scholar 

  • Dawid A.P. (2004). Probability, causality and the empirical world: a Bayes–de Finetti–Popper–Borel synthesis. Statistical Science 19, 44–57

    Article  MATH  MathSciNet  Google Scholar 

  • Dawid A.P., Vovk V. (1999). Prequential probability: principles and properties. Bernoulli 5, 125–162

    Article  MATH  MathSciNet  Google Scholar 

  • Feldman J. (1958). Equivalence and perpendicularity of Gaussian measures. Pacific Journal of Mathematics 8, 699–708

    MATH  MathSciNet  Google Scholar 

  • Fujiwara, A. (2007). Randomness criteria in terms of α-divergences. IEEE Transactions on Information Theory (accepted for publication).

  • Greenwood P.E., Shiryaev A.N. (1985). Contiguity and the statistical invariance principle. New York, Gordon & Breach

    MATH  Google Scholar 

  • Hájek J. (1958). On a property of normal distribution of an arbitrary stochastic process (in Russian). Czechoslovak Mathematical Journal 8, 610–618

    MathSciNet  Google Scholar 

  • Jacod J., Shiryaev A.N. (2003). Limit theorems for stochastic processes (2nd ed.). Berlin, Springer

    MATH  Google Scholar 

  • Kabanov, Y.M., Liptser, R.S., Shiryaev, A.N. (1977). On the question of absolute continuity and singularity of probability measures. Mathematics of the USSR—Sbornik, 33, 203–221. Russian original: , 104, 227–247.

  • Kakutani S. (1948). On equivalence of infinite product measures. Annals of Mathematics 49, 214–224

    Article  MathSciNet  Google Scholar 

  • Kumon M., Takemura A., Takeuchi K. (2007). Game-theoretic versions of strong law of large numbers for unbounded variables. Stochastics 79, 449–468

    MATH  MathSciNet  Google Scholar 

  • Pukelsheim F. (1986). Predictable criteria for absolute continuity and singularity of two probability measures. Statistics and Decisions 4, 227–236

    MATH  MathSciNet  Google Scholar 

  • Rényi, A. (1961). On measures of information and entropy. In Proceedings of the fourth Berkeley symposium on mathematical statistics and probability (Vol. 1, pp. 547–561). Berkeley, CA: University of California Press.

  • Shafer, G., Vovk, V. (2001). Probability and finance: it’s only a game! New York: Wiley. Abridged Japanese translation (2006): Tokyo: Iwanami Shoten.

  • Shiryaev, A. N. (1996). Probability (2nd ed.). New York: Springer. Third Russian edition published in 2004.

  • Solomonoff R.J. (1978). Complexity-based induction systems: comparisons and convergence theorems. IEEE Transactions on Information Theory IT-24, 422–432

    Article  MathSciNet  Google Scholar 

  • Ville J. (1939). Etude critique de la notion de collectif. Paris, Gauthier-Villars

    Google Scholar 

  • Vovk, V. (1987a). On a randomness criterion. Soviet Mathematics Doklady, 35, 656–660. Russian original: , 294(6), 1298–1302.

    Google Scholar 

  • Vovk, V. (1987b). The law of the iterated logarithm for random Kolmogorov, or chaotic, sequences. Theory of Probability and its Applications, 32, 413–425. Russian original: , 32(3), 456–468.

  • Vovk, V. (1989). Prediction of stochastic sequences. Problems of Information Transmission, 25, 285–296. Russian original: , 25(4), 35–49.

  • Vovk V. (1993). A logic of probability, with application to the foundations of statistics (with discussion). Journal of the Royal Statistical Society B 55, 317–351

    MATH  MathSciNet  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Vladimir Vovk.

Additional information

This work was partially supported by EPSRC (grant EP/F002998/1), MRC (grant G0301107), and the Cyprus Research Promotion Foundation.

About this article

Cite this article

Vovk, V. Merging of opinions in game-theoretic probability. Ann Inst Stat Math 61, 969–993 (2009). https://doi.org/10.1007/s10463-007-0165-x

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10463-007-0165-x

Keywords

Navigation