Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors
From practical point of view, in a two-level hierarchical model, the variance of second-level usually has a tendency to change through sub-populations. The existence of this kind of local (or intrinsic ) heteroscedasticity is a major concern in the application of statistical modeling. The main purpo...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2017-02-01
|
| Series: | Journal of Statistical Theory and Applications (JSTA) |
| Subjects: | |
| Online Access: | https://www.atlantis-press.com/article/25872954.pdf |
| _version_ | 1811292211163168768 |
|---|---|
| author | S. K. Ghoreishi |
| author_facet | S. K. Ghoreishi |
| author_sort | S. K. Ghoreishi |
| collection | DOAJ |
| description | From practical point of view, in a two-level hierarchical model, the variance of second-level usually has a tendency to change through sub-populations. The existence of this kind of local (or intrinsic ) heteroscedasticity is a major concern in the application of statistical modeling. The main purpose of this study is to construct a Bayesian methodology via shrinkage priors in order to estimate the interesting parameters under local heteroscedasticity. The suggested methodology for this issue is to use of a class of the local-global shrinkage priors, called Dirichlet-Laplace priors. The optimal posterior concentration and straightforward posterior computation are the appealing properties of these priors. Two real data sets are analyzed to illustrate the proposed methodology. |
| first_indexed | 2024-04-13T04:41:06Z |
| format | Article |
| id | doaj.art-0043a855a9bf4f1f920de1d63751d268 |
| institution | Directory Open Access Journal |
| issn | 1538-7887 |
| language | English |
| last_indexed | 2024-04-13T04:41:06Z |
| publishDate | 2017-02-01 |
| publisher | Springer |
| record_format | Article |
| series | Journal of Statistical Theory and Applications (JSTA) |
| spelling | doaj.art-0043a855a9bf4f1f920de1d63751d2682022-12-22T03:01:58ZengSpringerJournal of Statistical Theory and Applications (JSTA)1538-78872017-02-0116110.2991/jsta.2017.16.1.5Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priorsS. K. GhoreishiFrom practical point of view, in a two-level hierarchical model, the variance of second-level usually has a tendency to change through sub-populations. The existence of this kind of local (or intrinsic ) heteroscedasticity is a major concern in the application of statistical modeling. The main purpose of this study is to construct a Bayesian methodology via shrinkage priors in order to estimate the interesting parameters under local heteroscedasticity. The suggested methodology for this issue is to use of a class of the local-global shrinkage priors, called Dirichlet-Laplace priors. The optimal posterior concentration and straightforward posterior computation are the appealing properties of these priors. Two real data sets are analyzed to illustrate the proposed methodology.https://www.atlantis-press.com/article/25872954.pdfGlobal-local priorsHeteroscedasticityHierarchical modelsSURE estimators. |
| spellingShingle | S. K. Ghoreishi Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors Journal of Statistical Theory and Applications (JSTA) Global-local priors Heteroscedasticity Hierarchical models SURE estimators. |
| title | Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors |
| title_full | Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors |
| title_fullStr | Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors |
| title_full_unstemmed | Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors |
| title_short | Bayesian analysis of hierarchical heteroscedastic linear models using Dirichlet-Laplace priors |
| title_sort | bayesian analysis of hierarchical heteroscedastic linear models using dirichlet laplace priors |
| topic | Global-local priors Heteroscedasticity Hierarchical models SURE estimators. |
| url | https://www.atlantis-press.com/article/25872954.pdf |
| work_keys_str_mv | AT skghoreishi bayesiananalysisofhierarchicalheteroscedasticlinearmodelsusingdirichletlaplacepriors |