ABSTRACT
Mixture models are widely used in statistical modeling since they can model situations which a simple model cannot adequately describe. In recent years, mixture modeling has been exploited mainly due to high-speed computers that can make tractable problems that occur when working with mixtures (e.g. estimation). Statistics has benefited immensely by the development of advanced computer machines and thus more sophisticated and complicated methodologies have been developed. Mixture models underlie the use of such methodologies in a wide spectrum of practical situations where the hypothesized models can be given a mixture interpretation as demonstrated in the sequel.
