Abstract
In this paper, we introduce the notion of \({\mathcal{M}}\) -decomposability of probability density functions in one dimension. Using \({\mathcal{M}}\) -decomposability, we derive an inequality that applies to all symmetric unimodal densities. Our inequality involves only the standard deviation of the densities concerned. The concept of \({\mathcal{M}}\) -decomposability can be used as a non-parametric criterion for mode-finding and cluster analysis.
Similar content being viewed by others
References
Anderson T.W. (1955). The integral of a symmetric unimodal function over a symmetric convex set and some probability inequalities. Proceedings of the American Mathematical Society 6: 170–176
Dharmadhikari S.W., Joag-Dev K. (1987). Unimodality, convexity and applications. New York, Academic
Hardy G., Littlewood J.E., Pòlya G. (1988). Inequalities (2nd ed). Cambridge, Cambridge University Press
Ibragimov I.A. (1956 in Russian). On the composition of unimodal distributions. Theory of Probability and its Applications 1: 255–260
Kotz S., Read C.B., Balakrishnan N., Vidakovic B. (2005). Encyclopedia of statistical sciences (16 Volume Set, 2nd ed). New York, John Wiley and Sons
Pòlya G., Szegö G. (1972). Problems and theorems in analysis I (English ed). Berlin, Springer
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Chia, N., Nakano, J. \({\mathcal{M}}\) -decomposability and symmetric unimodal densities in one dimension. Ann Inst Stat Math 61, 275–289 (2009). https://doi.org/10.1007/s10463-007-0144-2
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10463-007-0144-2