Covariance and comparison inequalities under quadrant dependence (Q343261)

The authors aim is to establish a number of results on the difference between a distribution of random vectors \([X, Y]\) and \([X', Y']\), where \(X'\) and \(Y'\) are independent and \(X'\) has the same law as \(X\) and \(Y'\) as \(Y\). They give special attention to positively quadrant dependent random variables \(X\) and \(Y\), \(H_{x,y}(t,s):=\operatorname{P}(X\leq t, Y\leq s)-\operatorname{P}(X\leq t)\operatorname{P}(Y\leq S)\geq0\). In this case the bounds \(H_{x,y}(t,s)\) are expressed in terms of Hoeffding covariance of \(X_jY\).