2008
DOI: 10.1007/s10182-008-0057-2
|View full text |Cite
|
Sign up to set email alerts
|

A likelihood ratio test for bimodality in two-component mixtures with application to regional income distribution in the EU

Abstract: Bimodality, Convergence analysis, Cross-sectional income distribution, Likelihood ratio test, Finite mixture,

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
47
0

Year Published

2011
2011
2020
2020

Publication Types

Select...
5
1

Relationship

2
4

Authors

Journals

citations
Cited by 47 publications
(48 citation statements)
references
References 25 publications
1
47
0
Order By: Relevance
“…In 2001 the hypothesis of unimodality can only be rejected at the 10% level, from 2002 on it cannot be rejected anymore. We confirm these results using the recently introduced likelihood ratio test for bimodality in twocomponent normal mixture models in mean and variance by Holzmann and Vollmer (2008). The corresponding p values are shown in column p HV .…”
Section: Repeatsupporting
confidence: 69%
“…In 2001 the hypothesis of unimodality can only be rejected at the 10% level, from 2002 on it cannot be rejected anymore. We confirm these results using the recently introduced likelihood ratio test for bimodality in twocomponent normal mixture models in mean and variance by Holzmann and Vollmer (2008). The corresponding p values are shown in column p HV .…”
Section: Repeatsupporting
confidence: 69%
“…The null hypothesis is bimodality. Based on simulation results Holzmann, and Vollmer (2008) conclude that the LR test outperforms slightly the Silverman's test while both tests outperform the Dip test when the density is symmetric and bimodal. When the density is asymmetric and bimodal the LR test outperforms Silverman's test.…”
Section: Copyright C 2014 University Of Perugia Electronic Press Allmentioning
confidence: 99%
“…Following Holzmann, and Vollmer (2008) we consider f (z; θ) θ ∈ Θ ⊂ R d be a parametric family of densities allowing for the two component mixture family namely,…”
Section: Copyright C 2014 University Of Perugia Electronic Press Allmentioning
confidence: 99%
See 1 more Smart Citation
“…If two-component mixtures under suitable parameter restrictions allow at most two modes, such as two-component normals with proportional covariances, or t-mixtures with equal degrees of freedom and covariances, one can use parametric methods to test for one against two modes in such a model by likelihood-ratio based methods, see Holzmann and Vollmer (2008) for univariate normal and von Mises mixtures. This requires explicit characterizations of the parameter constellations which yield unimodal or bimodal mixtures.…”
Section: Mclachlan Andmentioning
confidence: 99%