Distributional equivalence and structure learning for bow-free acyclic path diagrams
We consider the problem of structure learning for bow-free acyclic path diagrams (BAPs). BAPs can be viewed as a generalization of linear Gaussian DAG models that allow for certain hidden variables. We present a first method for this problem using a greedy score-based search algorithm. We also prove...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Published: |
Institute of Mathematical Statistics
2017
|
| _version_ | 1826282390805282816 |
|---|---|
| author | Nowzohour, C Maathuis, M Evans, R Buehlmann, P |
| author_facet | Nowzohour, C Maathuis, M Evans, R Buehlmann, P |
| author_sort | Nowzohour, C |
| collection | OXFORD |
| description | We consider the problem of structure learning for bow-free acyclic path diagrams (BAPs). BAPs can be viewed as a generalization of linear Gaussian DAG models that allow for certain hidden variables. We present a first method for this problem using a greedy score-based search algorithm. We also prove some necessary and some sufficient conditions for distributional equivalence of BAPs which are used in an algorithmic approach to compute (nearly) equivalent model structures. This allows us to infer lower bounds of causal effects. We also present applications to real and simulated datasets using our publicly available R-package. |
| first_indexed | 2024-03-07T00:43:08Z |
| format | Journal article |
| id | oxford-uuid:83bd7ba3-9ecc-4165-8608-10c2eb669fe6 |
| institution | University of Oxford |
| last_indexed | 2024-03-07T00:43:08Z |
| publishDate | 2017 |
| publisher | Institute of Mathematical Statistics |
| record_format | dspace |
| spelling | oxford-uuid:83bd7ba3-9ecc-4165-8608-10c2eb669fe62022-03-26T21:46:16ZDistributional equivalence and structure learning for bow-free acyclic path diagramsJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:83bd7ba3-9ecc-4165-8608-10c2eb669fe6Symplectic Elements at OxfordInstitute of Mathematical Statistics2017Nowzohour, CMaathuis, MEvans, RBuehlmann, PWe consider the problem of structure learning for bow-free acyclic path diagrams (BAPs). BAPs can be viewed as a generalization of linear Gaussian DAG models that allow for certain hidden variables. We present a first method for this problem using a greedy score-based search algorithm. We also prove some necessary and some sufficient conditions for distributional equivalence of BAPs which are used in an algorithmic approach to compute (nearly) equivalent model structures. This allows us to infer lower bounds of causal effects. We also present applications to real and simulated datasets using our publicly available R-package. |
| spellingShingle | Nowzohour, C Maathuis, M Evans, R Buehlmann, P Distributional equivalence and structure learning for bow-free acyclic path diagrams |
| title | Distributional equivalence and structure learning for bow-free acyclic path diagrams |
| title_full | Distributional equivalence and structure learning for bow-free acyclic path diagrams |
| title_fullStr | Distributional equivalence and structure learning for bow-free acyclic path diagrams |
| title_full_unstemmed | Distributional equivalence and structure learning for bow-free acyclic path diagrams |
| title_short | Distributional equivalence and structure learning for bow-free acyclic path diagrams |
| title_sort | distributional equivalence and structure learning for bow free acyclic path diagrams |
| work_keys_str_mv | AT nowzohourc distributionalequivalenceandstructurelearningforbowfreeacyclicpathdiagrams AT maathuism distributionalequivalenceandstructurelearningforbowfreeacyclicpathdiagrams AT evansr distributionalequivalenceandstructurelearningforbowfreeacyclicpathdiagrams AT buehlmannp distributionalequivalenceandstructurelearningforbowfreeacyclicpathdiagrams |