A new transformation of continuous unimodal asymmetric probability distributions into possibility distributions

Abstract This paper deals with a new transformation, so-called two-sided normalized (TSN), of continuous unimodal asymmetric probability distributions into possibility distributions. Many properties are derived and interpretations are discussed. A comparison with the optimal transformation is provided. In particular, the respective positions of right or left branches relative to the resulting optimal and TSN possibility distributions are given. It is also shown that the TSN transformation is the optimal transformation for the particular family of two-piece skewed distributions. The preservation of the asymmetry property is then analyzed and illustrated for several conventional asymmetric distributions and counter-examples of asymmetry preservation are provided. A multilinear approximation of the TSN transformation is finally proposed.

[1]  D. Dubois,et al.  When upper probabilities are possibility measures , 1992 .

[2]  Lin-An Chen,et al.  Parametric coverage interval , 2007 .

[3]  On measuring asymmetry and the reliability of the skewness measure , 1991 .

[4]  Prakash N. Patil,et al.  A measure of asymmetry , 2012 .

[5]  Guy Jumarie FURTHER RESULTS ON POSSIBILITY-PROBABILITY CONVERSION VIA RELATIVE INFORMATION AND INFORMATIONAL INVARIANCE , 1995 .

[6]  G. Mauris,et al.  A fuzzy approach for the expression of uncertainty in measurement , 2001 .

[7]  George J. Klir,et al.  A MATHEMATICAL ANALYSIS OF INFORMATION-PRESERVING TRANSFORMATIONS BETWEEN PROBABILISTIC AND POSSIBILISTIC FORMULATIONS OF UNCERTAINTY , 1992 .

[8]  A non-parametric coverage interval , 2008 .

[9]  M. Oussalah ON THE PROBABILITY/POSSIBILITY TRANSFORMATIONS:A COMPARATIVE ANALYSIS , 2000 .

[10]  Gilles Mauris,et al.  Representing and Approximating Symmetric and Asymmetric Probability Coverage Intervals by Possibility Distributions , 2009, IEEE Transactions on Instrumentation and Measurement.

[11]  Kenneth F. Wallis,et al.  The Two-Piece Normal, Binormal, or Double Gaussian Distribution: Its Origin and Rediscoveries , 2014, 1405.4995.

[12]  G. Klir,et al.  PROBABILITY-POSSIBILITY TRANSFORMATIONS: A COMPARISON , 1992 .

[13]  Hung T. Nguyen,et al.  Possibility Theory, Probability and Fuzzy Sets Misunderstandings, Bridges and Gaps , 2000 .

[14]  Richard A. Groeneveld,et al.  Measuring Skewness and Kurtosis , 1984 .

[15]  Karl Pearson,et al.  Mathematical Contributions to the Theory of Evolution. XIX. Second Supplement to a Memoir on Skew Variation , 1901 .

[16]  A. Ferrero,et al.  Possibility and probability: application examples and comparison of two different approaches to uncertainty evaluation , 2015 .

[17]  A. Azzalini A class of distributions which includes the normal ones , 1985 .

[18]  M. Steel,et al.  On Bayesian Modelling of Fat Tails and Skewness , 1998 .

[19]  Gilles Mauris,et al.  A Review of Relationships Between Possibility and Probability Representations of Uncertainty in Measurement , 2013, IEEE Transactions on Instrumentation and Measurement.

[20]  D. Dubois,et al.  On Possibility/Probability Transformations , 1993 .

[21]  L. Zadeh Fuzzy sets as a basis for a theory of possibility , 1999 .

[22]  Hannu Oja,et al.  On Location, Scale, Skewness and Kurtosis of Univariate Distributions , 2016 .

[23]  Shubhabrata Das,et al.  On homogeneous skewness of unimodal distributions , 2009 .

[24]  John W. Seaman,et al.  The efficacy of fuzzy representations of uncertainty , 1994, IEEE Trans. Fuzzy Syst..

[25]  M. C. Jones,et al.  Asymmetry and Gradient Asymmetry Functions: Density‐Based Skewness and Kurtosis , 2008 .

[26]  Kjell A. Doksum,et al.  Measures of Location and Asymmetry , 1975 .

[27]  Didier Dubois,et al.  Practical representations of incomplete probabilistic knowledge , 2006, Comput. Stat. Data Anal..

[28]  K. Pearson Contributions to the Mathematical Theory of Evolution. II. Skew Variation in Homogeneous Material , 1895 .

[29]  T. Sudkamp On probability-possibility transformations , 1992 .

[30]  G. Jumarie Possibility‐Probability Transformation: A New Result via Information Theory of Deterministic Functions , 1994 .

[31]  Didier Dubois,et al.  Représentation de la connaissance probabiliste incomplète Representation of incomplete probabilistic information , .

[32]  Didier Dubois,et al.  Probability-Possibility Transformations, Triangular Fuzzy Sets, and Probabilistic Inequalities , 2004, Reliab. Comput..

[33]  H. L. MacGillivray,et al.  Skewness and Asymmetry: Measures and Orderings , 1986 .

[34]  Didier Dubois,et al.  Fuzzy sets and systems ' . Theory and applications , 2007 .

[35]  M. Sampford Some Inequalities on Mill's Ratio and Related Functions , 1953 .