Correlation coefficients are used in statistics to measure the dependence between two variables. Kendall rank correlation coefficient is routinely used as a measure of association between two random variables in a number of circumstances in which the use of the Pearson correlation coefficient is inappropriate. In this thesis, we develop an influence function-based empirical likelihood interval for the Kendall rank correlation coefficient. Simulation studies are conducted to show good finite sample properties and robustness of the proposed method compared with existing methods. The proposed method is illustrated on a real UCLA graduate dataset.