Simulation Study For Consistency Of Rosenblatt And Nearest Neighbors Estimates

Rosenblatt and Nearest neighbors estimates are the nonparametric estimation of the probability density function. Many authors have studied weak and strong consistency, strong consistent rates, uniformly weak and strong consistency, uniformly strong consistent rates and distribution properties of the two estimates with different condition since they mentioned by Rosenblatt and Loftsgarden & Quesenberry. The main work of this thesis is simulation study on the basis of large sample properties for two estimates by Monte Carlo method with some models. We consider the problem of the choice of window width, consistent rate and some doubtful points about consistent rate with fixed sample size.