Abstract
It is well known that joint bivariate densities cannot always be characterized by the corresponding two conditional densities. Hence, additional requirements have to be imposed. In the form of a conjecture, Arnold et al. (J Multivar Anal 99:1383–1392, 2008) suggested using any one of the two conditional densities and replacing the other one by the corresponding conditional percentile function. In this article we establish, in affirmative, this conjecture and provide several illustrative examples.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Arnold BC (1983) Pareto distributions. International Cooperative Publishing House, Fairland, MD
Arnold BC, Gokhale DV (1994) On uniform marginal representations of contingency tables. Stat Probab Lett 21:311–316
Arnold BC, Gokhale DV (1998) Distributions most nearly compatible with given families of conditional distributions. The finite discrete case. Test 7:377–390
Arnold BC, Castillo E, Sarabia JM (1996) Specification of distributions by combinations of marginal and conditional distributions. Stat Probab Lett 26:153–157
Arnold BC, Castillo E, Sarabia JM (1999) Conditional specification of statistical models. Springer, New York
Arnold BC, Castillo E, Sarabia JM (2001a) Quantification of incompatibility of conditional and marginal information. Commun Stat Theory Methods 30:381–395
Arnold BC, Castillo E, Sarabia JM (2001b) Conditionally specified distributions: an introduction. Stat Sci 16:249–265
Arnold BC, Castillo E, Sarabia JM (2008) Bivariate distributions characterized by one family of conditionals and conditional percentile or mode functions. J Multivar Anal 99:1383–1392
Asimit V, Vernic R, Zitikis R (2013) Evaluating risk measures and capital allocations based on multi-losses driven by a heavy-tailed background risk: the multivariate Pareto-II model. Risk 1(1):14–33
Asimit V, Vernic R, Zitikis R (2016) Background risk models and stepwise portfolio construction. Methodol Comput Appl Probab 18:805–827
Balakrishnan N, Lai CD (2009) Continuous bivariate distributions, 2nd edn. Springer, New York
Cacoullos T, Papageorgiou H (1995) Characterizations of discrete distributions by a conditional distribution and a regression function. Ann Inst Stat Math 35:95–103
Castillo E, Galambos J (1987) Lifetime regression models based on a functional equation of physical nature. J Appl Probab 24:160–169
Ghosh I, Balakrishnan N (2014) Partial or complete characterization of a bivariate distribution based on one conditional distribution and partial specification of the mode function of the other conditional distribution. Stat Methodol 16:1–13
Satterthwaite SP, Hutchinson TP (1978) A generalization of Gumbel’s bivariate logistic distribution. Metrika 25:163–170
Song CC, Li LA, Chen CH (2010) Compatibility of finite discrete conditional distributions. Stat Sin 20:423–440
Tan M, Tian GL, Ng KW (2010) Bayesian missing data problems: EM, data augmentation and non-iterative computation. Chapman and Hall, Boca Raton
Tian GL, Tan M, Ng KW, Tang ML (2009) A unified method for checking compatibility and uniqueness for finite discrete conditional distributions. Commun Stat Theory Methods 38:115–129
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The corresponding author states that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Ghosh, I. A complete characterization of bivariate densities using the conditional percentile function. Metrika 81, 485–492 (2018). https://doi.org/10.1007/s00184-018-0652-5
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00184-018-0652-5