On the invariant properties of notions of positive dependence and copulas under increasing transformations (Q2427805): Difference between revisions

The authors consider various kinds of positive dependence. They study the conditionally increase (CI), conditionally increase in sequence (CIS), positive dependence through the stochastic ordering (PDS) and positive dependence through the upper orthant ordering (PDUO) random vectors. The invariant properties under increasing and strongly increasing transformations are examined for CI, CIS, PDS and PDUO random vectors. The obtained results correct and extend the assertion of Theorem 3.10.19 of \textit{A. Müller} and \textit{D. Stoyan} [Comparison methods for stochastic models and risks. Wiley Series in Probability and Statistics. Chichester: Wiley. (2002; Zbl 0999.60002)]. In addition, the authors give a rigorous proof for the invariant property of copulas under increasing transformations on the components of any random vector. For this, the authors use the properties of generalized left-continuous and right-continuous inverse functions. The obtain copulas property generalizing Proposition 4.7.4 of \textit{M. Denuit} et al. [Actuarial theory for dependent risks: measures, orders and models. Chichester: John Wiley \& Sons (2005)] and Proposition 5.6 of \textit{A. J. McNeil, R. Frey} and \textit{P. Embrechts} [Quantative risk management: concepts, techniques and tools. Princeton Series in Finance. Princeton, NJ: Princeton University Press. (2005; Zbl 1089.91037)].