A0256
Title: Weighted likelihood methods for torus data
Authors: Claudio Agostinelli - University of Trento (Italy) [presenting]
Luca Greco - University G. Fortunato of Benevento (Italy)
Giovanni Saraceno - University at Buffalo (United States)
Abstract: Robust estimation of wrapped models to multivariate circular data (torus data) is considered based on the weighted likelihood methodology. Robust model fitting is achieved by a set of estimating equations based on the computation of data-dependent weights aimed to down-weight anomalous values, such as unexpected directions that do not share the main pattern of the bulk of the data. To solve these equations, an algorithm based on a data augmentation approach and a suitable modification of the expectation-maximization (EM) algorithm is proposed. The advantages and disadvantages of a classification EM algorithm are also discussed. Asymptotic properties and robustness features of the estimators under study are presented, whereas their finite sample behavior has been investigated by Monte Carlo numerical experiment and real data examples.
