U-statistic for co-skewness

40 Views Asked by At

I would like to develop the U-statistic for co-skewness. Specifically, let $X$ and $Y$ be two random variables, the co-skewness is $E[X-E(X)(Y-E(Y))^2]$. Then what is the corresponding U-statistic kernel? I thought it should be $(x_1-x_2)(y_1-y_2)^2$. But seems it is not right. Can anyone help? Many thanks.