Nelson-Aalen kernel estimator to the tail index of right censored Pareto-type data
摘要
Based on Nelson-Aalen product-limit estimator for randomly right-censored data, we propose a kernel-based estimator to the tail index of Pareto-type distributions under censoring. Under suitable regularity conditions, we establish its consistency and asymptotic normality. A simulation study shows that the smoothed estimator outperforms the non-smoothed version in terms of stability, bias, and mean squared error (MSE). Finally, an application to insurance loss data illustrates the practical usefulness of the method.