Universidad Complutense de Madrid
E-Prints Complutense

Divergence-based estimation and testing with misclassified data

Impacto

Downloads

Downloads per month over past year

Landaburu Jiménez, María Elena and Morales González, Domingo and Pardo Llorente, Leandro (2005) Divergence-based estimation and testing with misclassified data. Statistical Papers, 46 (3). pp. 397-409. ISSN 0932-5026

[img] PDF
Restringido a Repository staff only

538kB

Official URL: http://www.springerlink.com/content/j151063g0r87lg10/fulltext.pdf


URLURL Type
http://www.springerlink.com/Publisher


Abstract

The well-known chi-squared goodness-of-fit test for a multinomial distribution is generally biased when the observations are subject to misclassification. In Pardo and Zografos (2000) the problem was considered using a double sampling scheme and phi-divergence test statistics. A new problem appears if the null hypothesis is not simple because it is necessary to give estimators for the unknown parameters. In this paper the minimum phi-divergence estimators are considered and some of their properties are established. The proposed phi-divergence test statistics are obtained by calculating phi-divergences between probability density functions and by replacing parameters by their minimum phi-divergence estimators in the derived expressions. Asymptotic distributions of the new test statistics are also obtained. The testing procedure is illustrated with an example


Item Type:Article
Uncontrolled Keywords:Misclassification; Double sampling; Divergence estimators; Goodness-of-fit tests; Divergence statistics
Subjects:Sciences > Statistics > Sampling (Statistics)
ID Code:16459
Deposited On:20 Sep 2012 09:05
Last Modified:19 Feb 2019 11:56

Origin of downloads

Repository Staff Only: item control page