A practical problem with large-scale survey data is the possible presence of overdispersion. It occurs when the data display more variability than is predicted by the variance-mean relationship. This article describes a probability distribution generated by a mixture of discrete random variables to capture uncertainty, feeling, and overdispersion. Specifically, several tests for detecting overdispersion will be implemented on the basis of the asymptotic theory for maximum likelihood estimators. We discuss the results of a simulation experiment concerning log-likelihood ratio, Wald, Score, and Profile tests. Finally, some real datasets are analyzed to illustrate the previous results.

Testing Overdispersion in CUBE Models / Iannario, Maria. - In: COMMUNICATIONS IN STATISTICS. SIMULATION AND COMPUTATION. - ISSN 0361-0918. - 45:5(2016), pp. 1621-1635. [10.1080/03610918.2014.936466]

Testing Overdispersion in CUBE Models

IANNARIO, MARIA
2016

Abstract

A practical problem with large-scale survey data is the possible presence of overdispersion. It occurs when the data display more variability than is predicted by the variance-mean relationship. This article describes a probability distribution generated by a mixture of discrete random variables to capture uncertainty, feeling, and overdispersion. Specifically, several tests for detecting overdispersion will be implemented on the basis of the asymptotic theory for maximum likelihood estimators. We discuss the results of a simulation experiment concerning log-likelihood ratio, Wald, Score, and Profile tests. Finally, some real datasets are analyzed to illustrate the previous results.
2016
Testing Overdispersion in CUBE Models / Iannario, Maria. - In: COMMUNICATIONS IN STATISTICS. SIMULATION AND COMPUTATION. - ISSN 0361-0918. - 45:5(2016), pp. 1621-1635. [10.1080/03610918.2014.936466]
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11588/649365
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 1
social impact