Robust estimation of mixing measures in finite mixture models
From MaRDI portal
Publication:2295018
Abstract: In finite mixture models, apart from underlying mixing measure, true kernel density function of each subpopulation in the data is, in many scenarios, unknown. Perhaps the most popular approach is to choose some kernel functions that we empirically believe our data are generated from and use these kernels to fit our models. Nevertheless, as long as the chosen kernel and the true kernel are different, statistical inference of mixing measure under this setting will be highly unstable. To overcome this challenge, we propose flexible and efficient robust estimators of the mixing measure in these models, which are inspired by the idea of minimum Hellinger distance estimator, model selection criteria, and superefficiency phenomenon. We demonstrate that our estimators consistently recover the true number of components and achieve the optimal convergence rates of parameter estimation under both the well- and mis-specified kernel settings for any fixed bandwidth. These desirable asymptotic properties are illustrated via careful simulation studies with both synthetic and real data.
Recommendations
- Robust estimation in finite mixture models
- Robust estimation for the order of finite mixture models
- Robust estimation in the normal mixture model
- Simultaneous robust estimation in finite mixtures: the continuous case
- scientific article; zbMATH DE number 6123069
- Robust estimators for the regression parameters of experiments with mixtures models
- Robust estimates of parameters of two-component mixture model
- Robust fitting of mixture regression models
- Mixture models, robustness, and sum of squares proofs
Cites work
- A Comparison of Minimum Distance and Maximum Likelihood Estimation of a Mixture Proportion
- A Graphical Technique for Determining the Number of Components in a Mixture of Normals
- Bayesian Density Estimation and Inference Using Mixtures
- Bayesian Model Selection in Finite Mixtures by Marginal Density Decompositions
- Consistent estimation of mixture complexity.
- Consistent estimation of the order of mixture models.
- Convergence of latent mixing measures in finite and infinite mixture models
- Convergence rates of parameter estimation for some weakly identifiable finite mixtures
- Deconvolution with unknown error distribution
- Efficiency versus robustness: The case for minimum Hellinger distance and related methods
- Finite mixture models
- scientific article; zbMATH DE number 1085980 (Why is no real title available?)
- scientific article; zbMATH DE number 194758 (Why is no real title available?)
- Identifiability of Mixtures
- Inference for mixtures of symmetric distributions
- Inference on the order of a normal mixture
- Minimum Hellinger distance estimates for parametric models
- Minimum Hellinger Distance Estimation for Finite Mixture Models
- Minimum Hellinger distance estimation in a nonparametric mixture model
- Mixture models: theory, geometry and applications
- Non-Parametric Identification and Estimation of the Number of Components in Multivariate Mixtures
- On strong identifiability and convergence rates of parameter estimation in finite mixtures
- Optimal rate of convergence for finite mixture models
- Optimal Transport
- Order selection in finite mixture models with a nonsmooth penalty
- Robust and efficient estimation under data grouping
- Robust Bayesian inference via coarsening
- Robust estimation of mixing measures in finite mixture models
- Robust Estimation of Mixture Complexity
- Semiparametric estimation of a two-component mixture model
- Singularity structures and impacts on parameter estimation in finite mixtures of distributions
- Strong identifiability and optimal minimax rates for finite mixture estimation
- Testing the order of a model using locally conic parametrization: Population mixtures and stationary ARMA processes
- The ``automatic robustness of minimum distance functionals
- The estimation of the order of a mixture model
- The multivariate skew-normal distribution
Cited in
(16)- Robust estimation of mixture complexity for count data
- Robust estimation of \(k\)-component univariate normal mixtures
- On posterior contraction of parameters and interpretability in Bayesian mixture modeling
- A constrained robust proposal for mixture modeling avoiding spurious solutions
- Estimating the number of components in finite mixture models via the group-sort-fuse procedure
- Robust estimation of mixing measures in finite mixture models
- Qualitative robustness of von Mises statistics based on strongly mixing data
- Robust mixing
- Optimal Bayesian estimation of Gaussian mixtures with growing number of components
- The REBMIX Algorithm and the Univariate Finite Mixture Estimation
- The robust estimation method for a finite mixture of Poisson mixed-effect models
- scientific article; zbMATH DE number 6123069 (Why is no real title available?)
- Robust mixture model cluster analysis using adaptive kernels
- scientific article; zbMATH DE number 5063708 (Why is no real title available?)
- Bayesian Clustering via Fusing of Localized Densities
- Estimation and inference for the Wasserstein distance between mixing measures in topic models
This page was built for publication: Robust estimation of mixing measures in finite mixture models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2295018)
