Influence diagnostics on the coefficient of variation of elliptically contoured distributions
Autor
Riquelme-Álamos, Marco
Leiva, Víctor
Galea, Manuel
Sanhueza, Antonio
Fecha
2011Resumen
In this article, we study the behavior of the coefficient of variation (CV) of a random variable that follows a symmetric distribution in the real line. Specifically, we estimate this coefficient using the maximumlikelihood (ML) method. In addition, we provide asymptotic inference for this parameter, which allows us to contrast hypothesis and construct confidence intervals. Furthermore, we produce influence diagnostics to evaluate the sensitivity of the ML estimate of this coefficient when atypical data are present. Moreover, we illustrate the obtained results by using financial real data. Finally, we carry out a simulation study to detect the potential influence of atypical observations on the ML estimator of the CV of a symmetric distribution.
The illustration and simulation demonstrate the robustness of the ML estimation of this coefficient.
Fuente
Journal of Applied Statistics, 38(3), 513-532Link de Acceso
Click aquí para ver el documentoIdentificador DOI
doi.org/10.1080/02664760903521427Colecciones
La publicación tiene asociados los siguientes ficheros de licencia: