Robustness properties of multivariate S-estimators
Unveiling the resilience and reliability in a multivariate statistical analysis
More Info
expand_more
expand_more
Abstract
This thesis investigates the robustness of multivariate S-estimators, which are statistical methods used to estimate the location and covariance parameters of multivariate distributions. Outliers, or atypical observations, can significantly impact statistical analyses, leading to incorrect conclusions. Robust methods, such as S-estimators, aim to reduce the influence of outliers, providing more reliable analysis results.
The primary objective is to assess the effectiveness of S-estimators through simulations using the statistical package R.
Files
Bsc_thesis_CMarrone.pdf
(pdf | 3.04 Mb)