Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.01713 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917456236249088 |
|---|---|
| author | Lim, Heeju Diniz, Carlos A. R. Harel, Ofer Lachos, Victor H. |
| author_facet | Lim, Heeju Diniz, Carlos A. R. Harel, Ofer Lachos, Victor H. |
| contents | We introduce a novel matrix-variate extension of the Heckman selection model to accommodate multiple outcomes, providing a flexible and natural generalization of classical selection models for matrix-valued data. By relying on the matrix normal distribution, the proposed model captures dependencies across both rows and columns while accounting for selection bias. An Expectation/Conditional Maximization (ECM) algorithm is developed, yielding closed-form updates for all model parameters. We investigate key theoretical properties, including the connection between sample selection models and the recently developed multivariate unified skew-normal (SUN) distribution. The performance of the proposed approach is assessed through simulation studies, and its practical utility is illustrated using two real datasets. The proposed method is implemented in the R package mvHeckman. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01713 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multiple Heckman Selection Model Lim, Heeju Diniz, Carlos A. R. Harel, Ofer Lachos, Victor H. Methodology We introduce a novel matrix-variate extension of the Heckman selection model to accommodate multiple outcomes, providing a flexible and natural generalization of classical selection models for matrix-valued data. By relying on the matrix normal distribution, the proposed model captures dependencies across both rows and columns while accounting for selection bias. An Expectation/Conditional Maximization (ECM) algorithm is developed, yielding closed-form updates for all model parameters. We investigate key theoretical properties, including the connection between sample selection models and the recently developed multivariate unified skew-normal (SUN) distribution. The performance of the proposed approach is assessed through simulation studies, and its practical utility is illustrated using two real datasets. The proposed method is implemented in the R package mvHeckman. |
| title | Multiple Heckman Selection Model |
| topic | Methodology |
| url | https://arxiv.org/abs/2605.01713 |