Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm
Finite mixtures normal regression (FMNR) models are widely used to investigate the relationship between a response variable and a set of explanatory variables from several unknown latent homogeneous groups. However, the classical EM algorithm and Gibbs sampling to deal with this model have several w...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/9/6/590 |
| _version_ | 1797541887820693504 |
|---|---|
| author | Ang Shan Fengkai Yang |
| author_facet | Ang Shan Fengkai Yang |
| author_sort | Ang Shan |
| collection | DOAJ |
| description | Finite mixtures normal regression (FMNR) models are widely used to investigate the relationship between a response variable and a set of explanatory variables from several unknown latent homogeneous groups. However, the classical EM algorithm and Gibbs sampling to deal with this model have several weak points. In this paper, a non-iterative sampling algorithm for fitting FMNR model is proposed from a Bayesian perspective. The procedure can generate independently and identically distributed samples from the posterior distributions of the parameters and produce more reliable estimations than the EM algorithm and Gibbs sampling. Simulation studies are conducted to illustrate the performance of the algorithm with supporting results. Finally, a real data is analyzed to show the usefulness of the methodology. |
| first_indexed | 2024-03-10T13:22:05Z |
| format | Article |
| id | doaj.art-355fb6733a80416dbc2aff71ba9e02b4 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-10T13:22:05Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-355fb6733a80416dbc2aff71ba9e02b42023-11-21T09:54:08ZengMDPI AGMathematics2227-73902021-03-019659010.3390/math9060590Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative AlgorithmAng Shan0Fengkai Yang1School of Mathematics, Shandong University, Jinan 250100, ChinaSchool of Mathematics and Statistics, Shandong University, Weihai 264209, ChinaFinite mixtures normal regression (FMNR) models are widely used to investigate the relationship between a response variable and a set of explanatory variables from several unknown latent homogeneous groups. However, the classical EM algorithm and Gibbs sampling to deal with this model have several weak points. In this paper, a non-iterative sampling algorithm for fitting FMNR model is proposed from a Bayesian perspective. The procedure can generate independently and identically distributed samples from the posterior distributions of the parameters and produce more reliable estimations than the EM algorithm and Gibbs sampling. Simulation studies are conducted to illustrate the performance of the algorithm with supporting results. Finally, a real data is analyzed to show the usefulness of the methodology.https://www.mdpi.com/2227-7390/9/6/590finite mixture regressionnon-iterative samplingmissing dataGibbs samplingEM algorithm |
| spellingShingle | Ang Shan Fengkai Yang Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm Mathematics finite mixture regression non-iterative sampling missing data Gibbs sampling EM algorithm |
| title | Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm |
| title_full | Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm |
| title_fullStr | Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm |
| title_full_unstemmed | Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm |
| title_short | Bayesian Inference for Finite Mixture Regression Model Based on Non-Iterative Algorithm |
| title_sort | bayesian inference for finite mixture regression model based on non iterative algorithm |
| topic | finite mixture regression non-iterative sampling missing data Gibbs sampling EM algorithm |
| url | https://www.mdpi.com/2227-7390/9/6/590 |
| work_keys_str_mv | AT angshan bayesianinferenceforfinitemixtureregressionmodelbasedonnoniterativealgorithm AT fengkaiyang bayesianinferenceforfinitemixtureregressionmodelbasedonnoniterativealgorithm |