Bias Free Threshold Estimation for Jump Intensity Function

In this paper, combining the threshold technique, we reconstruct Nadaraya-Watson estimation using Gamma asymmetric kernels for the unknown jump intensity function of a diffusion process with finite activity jumps. Under mild conditions, we obtain the asymptotic normality for the proposed estimator. Moreover, we have verified the better finite-sampling properties such as bias correction and efficiency gains of the underlying estimator compared with other nonparametric estimators through a Monte Carlo experiment.