## Bernoulli

• Bernoulli
• Volume 5, Number 1 (1999), 125-162.

### Prequential probability: principles and properties

#### Abstract

Forecaster has to predict, sequentially, a string of uncertain quantities $( X 1,X 2,...)$, whose values are determined and revealed, one by one, by Nature. Various criteria may be proposed to assess Forecaster's empirical performance. The weak prequential principle requires that such a criterion should depend on Forecaster's behaviour or strategy only through the actual forecasts issued. A wide variety of appealing criteria are shown to respect this principle. We further show that many such criteria also obey the strong prequential principle, which requires that, when both Nature and Forecaster make their choices in accordance with a common joint distribution $P$ for $( X 1,X 2,...)$, certain stochastic properties, underlying and justifying the criterion and inferences based on it, hold regardless of the detailed specification of $P$. In order to understand further this compliant behaviour, we introduce the prequential framework, a game-theoretic basis for probability theory in which it is impossible to violate the prequential principles, and we describe its connections with classical probability theory. In this framework, in order to show that some criterion for assessing Forecaster's empirical performance is valid, we have to exhibit a winning strategy for a third player, Statistician, in a certain perfect-information game. We demonstrate that many performance criteria can be formulated and are valid in the framework and, therefore, satisfy both prequential principles.

#### Article information

Source
Bernoulli, Volume 5, Number 1 (1999), 125-162.

Dates
First available in Project Euclid: 12 March 2007

Permanent link to this document
https://projecteuclid.org/euclid.bj/1173707098

Mathematical Reviews number (MathSciNet)
MR1673572

Zentralblatt MATH identifier
0929.60001

#### Citation

Philip Dawid, A.; Vovk, Vladimir G. Prequential probability: principles and properties. Bernoulli 5 (1999), no. 1, 125--162. https://projecteuclid.org/euclid.bj/1173707098

#### References

• [1] Billingsley, P. (1986) Probability and Measure, 2nd edn. New York: Wiley.
• [2] Cox, D.R. and Lewis, P.A.W. (1966) Statistical Analysis of Series of Events. London: Methuen.
• [3] Dawid, A.P. (1982) The well-calibrated Bayesian (with discussion). J. Amer. Statist. Ass., 77, 605-613.
• [4] Dawid, A.P. (1983) Inference, statistical: I. In S. Kotz, N.L. Johnson and C.B. Read (eds), Encyclopedia of Statistical Sciences, Vol. 4, pp. 89-105. New York: Wiley-Interscience.
• [5] Dawid, A.P. (1984) Statistical theory: the prequential approach (with discussion). J. Roy. Statist. Soc. A, 147, 278-292.
• [6] Dawid, A.P. (1985) Calibration-based empirical probability (with discussion). Ann. Statist., 13, 1251-1285.
• [7] Dawid, A.P. (1986) Probability forecasting. In S. Kotz, N.L. Johnson and C.B. Read (eds), Encyclopedia of Statistical Sciences, Vol. 7, pp. 210-218. New York: Wiley-Interscience.
• [8] Dawid, A.P. (1991) Fisherian inference in likelihood and prequential frames of reference (with discussion). J. Roy. Statist. Soc. B, 53, 79-109.
• [9] Dawid, A.P. (1992a) Prequential data analysis. In M. Ghosh and P.K. Pathak (eds), Current Issues in Statistical Inference: Essays in Honor of D. Basu pp. 113-126. IMS Lecture Notes,Monograph Ser. 17. Hayward, CA: Institute of Mathematical Statistics.
• [10] Dawid, A.P. (1992b) Prequential analysis, stochastic complexity and Bayesian inference (with discussion). In J.M. Bernardo, J. Berger, A.P. Dawid and A.F.M. Smith (eds), Bayesian Statistics 4, pp. 109-125. Oxford: Oxford University Press.
• [11] de Finetti, B. (1974) Theory of Probability, Vol 1. London: Wiley.
• [12] Doob, J.L. (1953) Stochastic Processes. New York: Wiley.
• [13] Hill, T.P. (1982) Conditional generalizations of strong laws which conclude the partial sums converge almost surely. Ann. Probab., 10, 828-830.
• [14] Loveland, D. (1969) On minimal program complexity measures. Proceedings of the First ACM Symposium on the Theory of Computing, pp. 61-66. New York: ACM Press.
• [15] Martin, D. (1975) Borel determinacy. Ann. Math., 102, 363-371.
• [16] Martin, D. (1990) An extension of Borel determinacy. Ann. Pure Appl. Logic, 49, 279-293.
• [17] Minozzo, M. (1996) On some aspects of the prequential and algorithmic approaches to probability and statistical theory. PhD Thesis, University of London.
• [18] Rosenblatt, M. (1952) Remarks on a multivariate transformation. Ann. Math. Statist., 23, 470-472.
• [19] Schnorr, C.P. (1970) Klassifikation der Zufallsgesetze nach Komplexität und Ordnung. Z. Wahrscheinlichkeitstheorie Verw. Geb., 16, 1-21.
• [20] Schnorr, C.P. (1971a) A unified approach to the definition of random sequences. Math. Systems Theory, 5, 246-258.
• [21] Schnorr, C.P. (1971b) Zufälligkeit und Wahrscheinlichkeit. Berlin: Springer-Verlag.
• [22] Seillier-Moiseiwitsch, F. and Dawid, A.P. (1993) On testing the validity of sequential probability forecasts. J. Am. Statist. Assoc., 88, 355-359.
• [23] Shafer, G. (1976) A Mathematical Theory of Evidence. Princeton, NJ: Princeton University Press.
• [24] Shafer, G. (1996) The Art of Causal Conjecture. Cambridge, MA: MIT Press.
• [25] Shiryayev, A.N. (1984) Probability. New York: Springer-Verlag.
• [26] Stout, W.F. (1970) A martingale analogue of Kolmogorov's law of the iterated logarithm. Z. Wahrscheinlichkeitstheorie Verw. Geb., 15, 279-290.
• [27] Stout, W.F. (1974) Almost Sure Convergence. New York: Academic Press.
• [28] Ville, J. (1939) Etude Critique de la Notion de Collectif. Paris: Gauthier-Villars.
• [29] Vovk, V.G. (1987) The law of the iterated logarithm for random Kolmogorov, or chaotic, sequences. Theory Probab. Applic., 32, 413-425.
• [30] Vovk, V.G. (1988) Kolmogorov-Stout law of the iterated logarithm. Math. Notes, 44, 502-507.
• [31] Vovk, V.G. (1993a) A logic of probability, with application to the foundations of statistics (with discussion). J. Roy. Statist. Soc. B, 55, 317-351.
• [32] Vovk, V.G. (1993b) Forecasting point and continuous processes: prequential analysis. Test, 2, 189-217.
• [33] Vovk, V.G. (1996) A purely martingale version of Kolmogorov's strong law of large numbers. Theory Probab. Applic., 41, 605-608.