Mixture Models with a Black-Hole Component
暂无分享,去创建一个
We define a class of mixture models in which a component comprises an assortment of units that are not associated with any proper distribution. The models, motivated by the EM algorithm and fitted by its simple adaptation, are illustrated on several examples with large samples, one of them about transactions of residential properties in Wellington, New Zealand, in 2006.
[1] Nicholas T. Longford,et al. A house price index defined in the potential outcomes framework , 2009 .
[2] Geoffrey J. McLachlan,et al. Finite Mixture Models , 2019, Annual Review of Statistics and Its Application.
[3] Rajesh N. Davé,et al. Characterization and detection of noise in clustering , 1991, Pattern Recognit. Lett..
[4] D. Rubin,et al. Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .