PROPOSTAS DE NOVOS ESTIMADORES TIPO JAMES-STEIN E SUAS PROPRIEDADES VIA SIMULAÇÃO COMPUTACIONAL
Main Article Content
Abstract
The James-Stein estimator for the mean of an independent multivariate normal with equal variances is obtained by adaptive shrinkage of the sample mean estimator. This estimator dominates the mean estimator for dimensions greater or equal than three. In this work, we present variations of this estimator for the independent normal case with unequal variances and for the general case where the estimator is obtained using the Mahalanobis' metric. Geometric justications and a study of the behavior of these estimators by computational simulation for dimension three are presented using the mean square error as a measure of quality.
Article Details
How to Cite
GAJO, C. A., CHAVES, L. M., & SOUZA, D. J. de. (2017). PROPOSTAS DE NOVOS ESTIMADORES TIPO JAMES-STEIN E SUAS PROPRIEDADES VIA SIMULAÇÃO COMPUTACIONAL. Brazilian Journal of Biometrics, 35(4), 753–764. Retrieved from https://biometria.ufla.br/index.php/BBJ/article/view/121
Issue
Section
Articles
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).