Local influence diagnostics in elliptical multilevel models
Local influence diagnostics for elliptical multilevel models are proposed in this paper. This class of models involves the use of continuous symmetric distributions, including heavy-tailed error models, and the normal distribution as a particular case. Maximum likelihood estimation and features related to the fitting and model assumptions are discussed. Finally, local influence measures under different perturbation schemes are developed and applied to fit real data under the normal, Student- t and power exponential distributions.
Authors
- Audrey H. M. A. Cysneiros (ORCID: https://orcid.org/0000-0002-8920-4004)
- Roberto Ferreira Manghi (ORCID: https://orcid.org/0000-0002-5212-5118)
- E. Nogueira (ORCID: https://orcid.org/0000-0001-9381-3059)
Institutions
- Universidade Federal de Pernambuco (BR)
Publication Details
- Journal
- Anais da Academia Brasileira de Ciências
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1590/0001-3765202520240796
- Primary Topic
- Statistical Distribution Estimation and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco