2016/10/01 by Nawel Haouas, Haouas, Nawel, Abdelhakim Necir +3
Economics, Econometrics and Finance · #Financial Risk and Volatility Modeling #Monetary Policy and Economic Impact #Insurance and Financial Risk Management
paper · pdf · doi:10.48550/arxiv.1610.00094
In this paper, we propose an estimator of the second-order parameter of\nrandomly right-truncated Pareto-type distributions data and establish its\nconsistency and asymptotic normality. Moreover, we derive an asymptotically\nunbiased estimator of the tail index and study its asymptotic behaviour. Our\nconsiderations are based on a useful Gaussian approximation of the tail\nproduct-limit process recently given by Benchaira et al. [Tail product-limit\nprocess for truncated data with application to extreme value index estimation.\nExtremes, 2016; 19: 219-251] and the results of Gomes et al. [Semi-parametric\nestimation of the second order parameter in statistics of extremes. Extremes,\n2002; 5: 387-414]. We show, by simulation, that the proposed estimators behave\nwell, in terms of bias and mean square error.\n