Bandwidth Selection for Kernel Density Estimation Based on QQ-Plot

A new algorithm for the estimation of probability density functions has been considered in the paper. This founds a large number of applications in the context of statistical signal processing problems, such as detection, estimation, filtering or pattern recognition and classification. The proposed approach relies on the QQ-plot technique. The estimates of the first and second order statistics of the observed random data are used together with a suboptimal piece-wise linear approximation of the QQ-plot, yielding a new class of pdfs estimators. The feasibility of the proposed approach is demonstrated by simulations. With respect to the obtained results, this approach provides better or comparable results related to the other commonly used techniques. Key-Words: qq-plot technique, probability density function estimation, piece-wise linear approximation