A modified likelihood ratio test for homogeneity in finite mixture models

By Hanfeng Chen, Jiahua Chen, John D. Kalbfleisch. 2001

261 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/b2b47d2642c71eeed37fdc8f41aad5becf12a069

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

Citations in the corpus

Order Selection in Finite Mixture Models With a Nonsmooth Penalty (2008, methodology): “Chen et al. (2001) reported that the choice of CK is not crucial, and this is reaffirmed by our simulations.”
Non-finite Fisher information and homogeneity: an EM approach (2009, methodology): “When the number of em-iterations tends to infinity and under the assumption that the em algorithm converges to a global maximum, the em-test statistic becomes the modified likelihood ratio test, see Chen (1998) and Chen et al.”
Inference for Subgroup Analysis With a Structured Logistic-Normal Mixture Model (2015, background): “Chen, Chen, and Kalbfleisch (2001) studied a penalized likelihood ratio test to restrict the mixing parameter from approaching 0 or 1.”
Testing the Order of a Finite Mixture (2010, methodology): “The modified likelihood ratio test (MLRT) proposed by Chen (1998) and Chen, Chen, and Kalbfleisch (2001) is easily implemented.”
Mixed Normal Conditional Heteroskedasticity (2004, background): “Unfortunately, standard test theory breaks down in this context; see, for example, Wolfe (1971), Everitt and Hand (1981), Aitkin et al. (1981), Hartigan (1985), Ghosh and Sen (1985) McLachlan and Peel (2000, Ch. 6), and Chen et al. (2001).”
Hypothesis testing in mixture regression models (2004, methodology): “Moreover, assumption 3 assumes the positive definitiveness of J.µ/, which is a generalization of the strong identifiability conditions that were used in Chen (1995) and Chen and Chen (2001).”
Testing Homogeneity in a Mixture Distribution via the L2 Distance Between Competing Models (2004, methodology): “We rst consider models (3) and (5), which are comparable to the cases examined by Chen et al. (2001).”
A likelihood ratio test for bimodality in two-component mixtures with application to regional income distribution in the EU (2008, methodology): “component mixtures has been extensively studied in recent years, cf. e.g. Chen et al. (2001) .”
Modified likelihood ratio test in finite mixture models with a structural parameter (2005, background): “When the structural parameter is known, the modified likelihood ratio statistic has a very simple limiting distribution of 0.5 21+ 0.5 20 under the null hypothesis k = 1 (Chen et al., 2001).”
Testing for a finite mixture model with two components (2004, methodology): “A slightly adjusted EM algorithm (Chen et al., 2001) is used to compute the maximummodified likelihood estimate of the mixing distribution.”
The Strategic Timing Incentives of Commercial Radio Stations: An Empirical Analysis Using Multiple Equilibria (2009, methodology): “6.1.1 Modified Likelihood Ratio Test (MLRT) MLRTs have been developed in the statistics literature (Chen et al. (2001) and Chen et al. (2004)) to test for the appropriate number of components in binomial mixture models.”