Document Type : Original Article
Author
Department of Statistics, Payame Noor University, Tehran, Iran,
Abstract
In this paper, we generalize the Farlie–Gumbel–Morgenstern (FGM) bivariate distribution function by incorporating an appropriate weighting function, thereby extending the FGM copula. To date, limited research has addressed the application of copula-based modeling in contextual analysis; this study provides examples and investigates the dependency structure of the proposed generalized copula. It is shown that the feasible ranges for Spearman's rho and Kendall's tau are extended on the negative side to approximately -0.75 and -0.50, respectively, while the upper bounds remain at 0.33 and 0.22. Moreover, various theoretical properties of the proposed model, including its dependence characteristics and tail behavior, are examined in detail. Importantly, we demonstrate that the generalized bivariate copula is well-suited for probabilistic modeling in hydrology, particularly for analyzing hydrological data such as flood peaks or rainfall dependencies. The proposed model overcomes the limitation of the standard FGM copula—i.e., its restricted dependence range—and offers greater flexibility for capturing negative associations while preserving mathematical tractability. Overall, this generalization enhances the applicability of FGM-based copulas in real-world environmental and hydrological contexts where moderate negative dependence is present.
Highlights
-
Generalizes the Farlie–Gumbel–Morgenstern (FGM) copula using a suitable weighting function.
-
Extends the attainable negative dependence range of Spearman’s rho and Kendall’s tau.
-
Examines the dependence structure and tail behavior of the generalized copula.
-
Demonstrates enhanced flexibility for modeling negative dependence in hydrological data.
-
Applies the proposed model to hydrological dependence analysis, including rainfall and flood peaks.
Keywords
bekrizadehAMS69-72-2012.pdf.
Likelihood ratio tests under nonstandard conditions. Journal of the American Statistical Association, 1987, 82(398), 605–610. https://doi.org/10.1080/01621459.1987.10478472.
[22] Rao, C.R. On discrete distributions arising out of methods of ascertainment. In G.P. Patil (Ed.), Classical and Contagious Discrete Distributions, Statistical Publishing Society and Pergamum Press, 1965, 320–332. https://www.jstor.org/stable/25049375.