Analytical Plug-In Method for Kernel Density Estimator Applied to Genetic Neutrality Study

Abstract

The plug-in method enables optimization of the bandwidth of the kernel density estimator in order to estimate probability density functions (pdfs). Here, a faster procedure than that of the common plug-in method is proposed. The mean integrated square error (MISE) depends directly upon J(f) which is linked to the second-order derivative of the pdf. As we intend to introduce an analytical approximation of J(f), the pdf is estimated only once, at the end of iterations. These two kinds of algorithm are tested on different random variables having distributions known for their difficult estimation. Finally, they are applied to genetic data in order to provide a better characterisation in the mean of neutrality of Tunisian Berber populations.