Finding Meaningful Bayesian Confirmation Measures

• Autorzy: Greco S. , Słowiński R. , Szczęch I.
• Języki publikacji: EN

Abstrakty

EN

The paper focuses on Bayesian confirmation measures used for evaluation of rules induced from data. To distinguish between many confirmation measures, their properties are analyzed. The article considers a group of symmetry properties. We demonstrate that the symmetry properties proposed in the literature focus on extreme cases corresponding to entailment or refutation of the rule's conclusion by its premise, forgetting intermediate cases. We conduct a thorough analysis of the symmetries regarding that the confirmation should express how much more probable the rule's hypothesis is when the premise is present rather than when the negation of the premise is present. As a result we point out which symmetries are desired for Bayesian confirmation measures. Next, we analyze a set of popular confirmation measures with respect to the symmetry properties and other valuable properties, being monotonicity M, Ex₁ and weak Ex₁, logicality L and weak L. Our work points out two measures to be the most meaningful ones regarding the considered properties.

Słowa kluczowe

EN

Bayesian confirmation measures; rule evaluation; symmetry properties

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 2013
• Tom: Vol. 127, nr 1-4
• Strony: 161--176
• Opis fizyczny: Bibliogr. 43 poz., tab.

Twórcy

autor

Greco S.

• Department of Economics & Business, University of Catania, Italy
• Portsmouth Business School, Operations & Systems Management, University of Portsmouth, United Kingdom

autor

Słowiński R.

• Institute of Computing Science, Poznan University of Technology, Poland
• Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland

autor

Szczęch I.

• Institute of Computing Science, Poznan University of Technology, Poland

Bibliografia

• [1] Agrawal, R., Imielinski, T., Swami, A.: Mining associations between sets of items in massive databases, Proc. of the 1993 ACM-SIGMOD Intl Conference on Management of Data, 1993.
• [2] Brzezinska, I., Greco, S., Slowinski, R.: Mining Pareto-optimal rules with respect to support and anti-support, Engineering Applications of Artificial Intelligence, 20(5), 2007, 587-600.
• [3] Carnap, R.: Logical Foundations of Probability, 2nd ed., University of Chicago Press, 1962.
• [4] Christensen, D.: Measuring confirmation, Jour, of Philosophy, 96, 1999, 437-461.
• [5] Crupi, V., Tentori, K., Gonzalez, M.: On Bayesian measures of evidential support: Theoretical and empirical issues, Philosophy of Science, 74, 2007, 229-252.
• [6] Earman, J.: Bayes or Bust: A Critical Examination of Bayesian Confirmation Theory, MIT Press, Cambridge, MA, 1992.
• [7] Eells, E.: Rational Decision and Causality, Cambridge University Press, Cambridge, 1982.
• [8] Eells, E., Fitelson, B.: Symmetries and asymmetries in evidential support, Philosophical Studies, 107(2), 2002, 129-142.
• [9] Fayyad, U., Piatetsky-Shapiro, G.and Smyth, P.: From data mining to knowledge discovery: an overview, Advances in Knowledge Discovery and Data Mining, AAAI Press, 1996.
• [10] Fitelson, B.: The Plurality of Bayesian Measures of Confirmation and the Problem of Measure Sensitivity, Philosophy of Science, 66, 1999, 362-378.
• [11] Fitelson, B.: Studies in Bayesian Confirmation Theory, Ph.D. Thesis, University of Wisconsin, Madison, 2001.
• [12] Fitelson, B.: Logical Foundations of Evidential Support, Philosophy of Science, 73, 2006, 500-512.
• [13] Geng, L., Hamilton, H.: Interestingness Measures for Data Mining: A Survey, ACM Computing Surveys, 38(3), 2006.
• [14] Gillies, D.: In defense of the PopperMiller argument, Philosophy of Science, 53, 1986, 110-113.
• [15] Good, I.: The best explicatum for weight of evidence, Journal of Statistical Computation and Simulation, 19, 1984, 294-299.
• [16] Greco, S., Pawlak, Z., Slowinski, R.: Can Bayesian confirmation measures be useful for rough set decision rules?, Engineering Applications of Artificial Intelligence, 17, 2004, 345-361.
• [17] Greco, S., Slowinski, R., Szczech, I.: Assessing the quality of rules with a new monotonic interestingness measure Z, Artificial Intelligence and Soft Computing (ICAISC 2008), Springer, 2008 , 556-565.
• [18] Greco, S., Slowinski, R., Szczech, I.: Analysis of symmetry properties for Bayesian confirmation measures, Rough Sets and Knowledge Technology, Springer-Verlag Berlin Heidelberg, 2012,207-214.
• [19] Greco, S., Slowinski, R., Szczech, I.: Properties of rule interestingness measures and alternative approaches to normalization of measures, Information Sciences, 216, 2012, 1-16.
• [20] Hamalainen, W.: Efficient Search Methods for Statistical Dependency Rules, Fundamenta Informaticae, 113(2), 2011, 117-150.
• [21] Heckerman, D.: An axiomatic framework for belief updates, Uncertainty in Artificial Intelligence, 2, 1988, 11-22.
• [22] Hempel, C.: Studies in the logic of confirmation (I), Mind, 54, 1945, 1-26.
• [23] Horvitz, E., Heckerman, D.: The inconsistent use of certainty measures in artificial intelligence research, Uncertainty in Artificial Intelligence, 1, 1986, 137-151.
• [24] Horwich, P.: Probability and Evidence, Cambridge University Press, Cambrigde, 1982.
• [25] Jeffrey, R.: Probability and the Art of Judgment, Cambridge University Press, Cambrigde, 1992.
• [26] Joyce, J.: The Foundations of Causal Decision Theory, Cambridge University Press, Cambridge, 1999.
• [27] Kemeny, J., Oppenheim, P.: Degrees of factual support, Philosophy of Science, 19, 1952, 307-324.
• [28] Keynes, J.: A Treatise on Probability, Macmillan, London, 1921.
• [29] Mackie, J.: The relevance criterion of confirmation, The British Journal for the Philosophy of Science, 20, 1969, 27-40.
• [30] Maher, P.: Confirmation Theory. The Encyclopedia of Philosophy (2nd ed.), Mac-millan Reference, USA, 2005.
• [31] McGarry, K.: A survey of interestingness measures for knowledge discovery, The Knowledge Engineering Review, 20(1), 2005,39-61.
• [32] Milne, P.: A Bayesian defence of Popperian science?, Analysis, 55, 1995, 213-215.
• [33] Mortimer, H.: The Logic of Induction, Paramus, Prentice Hall, 1988.
• [34] Nozick, R.: Philosophical Explanations, Clarendon Press, Oxford (UK), 1981.
• [35] Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference, Morgan Kaufman, San Francisco, 1988.
• [36] Pollard, S.: Milne’s measure of confirmation, Analysis, 59, 1999, 335-337.
• [37] Popper, K.: The Logic of Scientific Discovery, Hutchinson, London, 1959.
• [38] Rips, L.: Two Kinds of Reasoning, Psychological Science, 12, 2001, 129-134.
• [39] Rosenkrantz, R.: Bayesian confirmation: paradise regained, The British Journal for the Philosophy of Science, 45, 1994, 467-476.
• [40] Schlesinger, G.: Measuring degrees of confirmation, Analysis, 55, 1995, 208-212.
• [41] Schum, D.: The Evidential Foundations of Probabilistic Reasoning, Wiley, New York, 1994.
• [42] Szczech, I.: Multicriteria Attractiveness Evaluation of Decision and Association Rules, Transactions on Rough SetsX, LNCS series, 5656, 2009, 197-274.
• [43] Szczech, I., Greco, S., Slowinski, R.: New property for rule interestingness measures, Proceedings of the Federated Conference on Computer Science and Information Systems FedCSIS, 2011, 103-108.