You have no items in your shopping cart.
ABSTRACT
The Kernel Density Estimation (KDE) is a crucial part in Statistics, the two approaches to kernel density estimation is the parametric and nonparametric approach, the two most important parts is the selection of kernel function (k) and selection of bandwidth (h). In this research, we specialized on three methods of choosing bandwidths which include: Silverman's Rule of Thumb, Subjective method and Scott bandwidth. Also, an analysis was carried out on three different data using Python, and results shows that Silverman's Rule of Thumb outperformed the other two methods.
