Abstract The aim of this paper is to propose a semiparametric method for the estimation of the copula param- eters based on a nonlinear quantile regression model. The estimation of the dependence parameter has been selected as the value that minimizes the distance between one of the pseudo samples and the inverse of the quantile regression. A simulation study is performed to measure the performance of this method. The simulation results are compared to the maximum pseudo-likelihood (MPL) method and minimum pseudo-Hellinger distance (MPHD) method for well-known bivariate copula models. These results show that the proposed method based on the copula quantile regression model has a good performance in small sample sizes

Keywords