Robust estimation for circular data |
| |
Authors: | Claudio Agostinelli |
| |
Affiliation: | Dipartimento di Statistica, Università Ca’ Foscari, SanGiobbe, Cannaregio 873, 30121 Venezia, Italia |
| |
Abstract: | The problems arising when there are outliers in a data set that follow a circular distribution are considered. A robust estimation of the unknown parameters is obtained using the methods of weighted likelihood and minimum disparity, each of which is defined for a general parametric family of circular data. The class of power divergence and the related residual adjustment function is investigated in order to improve the performance of the two methods which are studied for the Von Mises (circular normal) and the Wrapped Normal distributions. The techniques are illustrated via two examples based on a real data set and a Monte Carlo study, which also enables the discussion of various computational aspects. |
| |
Keywords: | Circular data Disparity measures Kernel density estimation Outliers in circular data Residual adjustment function Robust estimation Weighted likelihood |
本文献已被 ScienceDirect 等数据库收录! |
|