Practically effective adjustment variable selection in causal inference
In the estimation of causal effects, one common method for removing the influence of confounders is to adjust the variables that satisfy the back-door criterion. However, it is not always possible to uniquely determine sets of such variables. Moreover, real-world data is almost always limited, which...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Journal of Physics: Complexity |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-072X/ada861 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832584246725705728 |
|---|---|
| author | Atsushi Noda Takashi Isozaki |
| author_facet | Atsushi Noda Takashi Isozaki |
| author_sort | Atsushi Noda |
| collection | DOAJ |
| description | In the estimation of causal effects, one common method for removing the influence of confounders is to adjust the variables that satisfy the back-door criterion. However, it is not always possible to uniquely determine sets of such variables. Moreover, real-world data is almost always limited, which means it may be insufficient for statistical estimation. Therefore, we propose criteria for selecting variables from a list of candidate adjustment variables along with an algorithm to prevent accuracy degradation in causal effect estimation. We initially focus on directed acyclic graphs (DAGs) and then outlines specific steps for applying this method to completed partially DAGs (CPDAGs). We also present and prove a theorem on causal effect computation possibility in CPDAGs. Finally, we demonstrate the practical utility of our method using both existing and artificial data. |
| format | Article |
| id | doaj-art-667c8ef7676545c0990ed72afbf85c46 |
| institution | Kabale University |
| issn | 2632-072X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Journal of Physics: Complexity |
| spelling | doaj-art-667c8ef7676545c0990ed72afbf85c462025-01-27T14:42:08ZengIOP PublishingJournal of Physics: Complexity2632-072X2025-01-016101500110.1088/2632-072X/ada861Practically effective adjustment variable selection in causal inferenceAtsushi Noda0https://orcid.org/0009-0000-3573-8062Takashi Isozaki1https://orcid.org/0009-0000-5697-7409Sony Corporation of America , Los Angeles, CA, United States of AmericaSony Computer Science Laboratories, Inc. , Tokyo, JapanIn the estimation of causal effects, one common method for removing the influence of confounders is to adjust the variables that satisfy the back-door criterion. However, it is not always possible to uniquely determine sets of such variables. Moreover, real-world data is almost always limited, which means it may be insufficient for statistical estimation. Therefore, we propose criteria for selecting variables from a list of candidate adjustment variables along with an algorithm to prevent accuracy degradation in causal effect estimation. We initially focus on directed acyclic graphs (DAGs) and then outlines specific steps for applying this method to completed partially DAGs (CPDAGs). We also present and prove a theorem on causal effect computation possibility in CPDAGs. Finally, we demonstrate the practical utility of our method using both existing and artificial data.https://doi.org/10.1088/2632-072X/ada861causal inferenceinterventionstructural causal modelsadjustment variablesDAGdo-calculus |
| spellingShingle | Atsushi Noda Takashi Isozaki Practically effective adjustment variable selection in causal inference Journal of Physics: Complexity causal inference intervention structural causal models adjustment variables DAG do-calculus |
| title | Practically effective adjustment variable selection in causal inference |
| title_full | Practically effective adjustment variable selection in causal inference |
| title_fullStr | Practically effective adjustment variable selection in causal inference |
| title_full_unstemmed | Practically effective adjustment variable selection in causal inference |
| title_short | Practically effective adjustment variable selection in causal inference |
| title_sort | practically effective adjustment variable selection in causal inference |
| topic | causal inference intervention structural causal models adjustment variables DAG do-calculus |
| url | https://doi.org/10.1088/2632-072X/ada861 |
| work_keys_str_mv | AT atsushinoda practicallyeffectiveadjustmentvariableselectionincausalinference AT takashiisozaki practicallyeffectiveadjustmentvariableselectionincausalinference |