\noindent We introduce new estimates and tests of independence in copula models with unknown margins using $\phi$-divergences and the duality technique. The asymptotic laws of the estimates and the test statistics are established both when the parameter is an interior or a boundary value of the parameter space. Simulation results show that the choice of $\chi^2$-divergence has good properties in terms of efficiency-robustness.
duality, divergences, copulas, dependence function, multivariate rank statistics, semiparametric inference, boundary
62F03, 62F10, 62F12, 62H12, 62H15