Discrete quasi-copulas (Q2567085)

The authors extend the theory of quasi-copulas to the bivariate discrete case and study various properties. A method of constructing quasi-copulas in the discrete case is also given. The method is illustrated by examples. A function \(C(x, y)\) is said to be a copula if it satisfies the conditions (a) \(C(0, x)= C(x, 0)= 0\) and \(C(1, x)= C(x, 1)= x\) for all \(x\) on a unit interval, and (b) \(C(x',y')+ C(x,y)\geq C(x',y)+ C(x, y')\) where \(x\), \(x'\), \(y\), \(y\)' are points on a unit interval with \(x\leq x'\) and \(y\leq y'\). If at least one of \(x\), \(x'\), \(y\), \(y'\) is either \(0\) or \(1\), then the copula is called a quasi-copula. The copulas arise in statistical theory when one wishes to represent a joint distribution function \(H(x, y)\) of two random variables \(x\) and \(y\) as \(H(x, y)= C(F(x), G(y))\) where \(F(x)\) and \(G(y)\) are the marginal distribution functions of \(x\) and \(y\), respectively.