Utilize este identificador para referenciar este registo: http://hdl.handle.net/10400.1/10438
Título: The presence of distortions in the extended skew: normal distribution
Autor: Seijas-Macias, António
Oliveira, Amílcar
Oliveira, Teresa
Palavras-chave: Skewness
Skew normal
Computational cumulants
Data: Mar-2017
Editora: ISI-RSC
Resumo: In the last years, a very interesting topic has arisen and became the research focus not only for many mathematicians and statisticians, as well as for all those interested in modeling issues: The Skew normal distributions’ family that represents a generalization of normal distribution. The first generalization was developed by Azzalini in 1985, which produces the skew-normal distribution, and introduces the existence of skewness into the normal distribution. Later on, the extended skew-normal distribution is defined as a generalization of skew-normal distribution. These distributions are potentially useful for the data that presenting high values of skewness and kurtosis. Applications of this type of distributions are very common in model of economic data, especially when asymmetric models are underlying the data. Definition of this type of distribution is based in four parameters: location, scale, shape and truncation. In this paper, we analyze the evolution of skewness and kurtosis of extended skew-normal distribution as a function of two parameters (shape and truncation). We focus in the value of kurtosis and skewness and the existence of arange of values where tiny modification of the parameters produces large oscillations in the values. The analysis shows that skewness and kurtosis present an instability development for greater values of truncation. Moreover, some values of kurtosis could be erroneous. Packages implemented in software R confirm the existence of a range where value of kurtosis presents a random evolution.
Peer review: yes
URI: http://hdl.handle.net/10400.1/10438
Aparece nas colecções:CAC3-Livros (ou partes, com ou sem arbitragem científica)

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
ISIRSC2017_IPS19_S3_P_Macias.pdf718,12 kBAdobe PDFVer/Abrir

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Degois 

Todos os registos no repositório estão protegidos por leis de copyright, com todos os direitos reservados.