Bias attenuation results for dichotomization of a continuous confounder
It is well-known that dichotomization can cause bias and loss of efficiency in estimation. One can easily construct examples where adjusting for a dichotomized confounder causes bias in causal estimation. There are additional examples in the literature where adjusting for a dichotomized confounder c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2022-12-01
|
| Series: | Journal of Causal Inference |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/jci-2022-0047 |
| _version_ | 1811171933875601408 |
|---|---|
| author | Gabriel Erin E. Peña Jose M. Sjölander Arvid |
| author_facet | Gabriel Erin E. Peña Jose M. Sjölander Arvid |
| author_sort | Gabriel Erin E. |
| collection | DOAJ |
| description | It is well-known that dichotomization can cause bias and loss of efficiency in estimation. One can easily construct examples where adjusting for a dichotomized confounder causes bias in causal estimation. There are additional examples in the literature where adjusting for a dichotomized confounder can be more biased than not adjusting at all. The message is clear, do not dichotomize. What is unclear is if there are scenarios where adjusting for the dichotomized confounder always leads to lower bias than not adjusting. We propose several sets of conditions that characterize scenarios where one should always adjust for the dichotomized confounder to reduce bias. We then highlight scenarios where the decision to adjust should be made more cautiously. To our knowledge, this is the first formal presentation of conditions that give information about when one should and potentially should not adjust for a dichotomized confounder. |
| first_indexed | 2024-04-10T17:22:39Z |
| format | Article |
| id | doaj.art-584d289c30f24f0788c8976752e942b9 |
| institution | Directory Open Access Journal |
| issn | 2193-3685 |
| language | English |
| last_indexed | 2024-04-10T17:22:39Z |
| publishDate | 2022-12-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Journal of Causal Inference |
| spelling | doaj.art-584d289c30f24f0788c8976752e942b92023-02-05T08:27:16ZengDe GruyterJournal of Causal Inference2193-36852022-12-0110151552610.1515/jci-2022-0047Bias attenuation results for dichotomization of a continuous confounderGabriel Erin E.0Peña Jose M.1Sjölander Arvid2Department of Public Health, Section of Biostatistics, University of Copenhagen, Copenhagen, DenmarkDepartment of Computer and Information Science, Linköping University, Linköping, SwedenDepartment of Medical Epidemiology and Biostatistics, Karolinska Institutet, Solna, SwedenIt is well-known that dichotomization can cause bias and loss of efficiency in estimation. One can easily construct examples where adjusting for a dichotomized confounder causes bias in causal estimation. There are additional examples in the literature where adjusting for a dichotomized confounder can be more biased than not adjusting at all. The message is clear, do not dichotomize. What is unclear is if there are scenarios where adjusting for the dichotomized confounder always leads to lower bias than not adjusting. We propose several sets of conditions that characterize scenarios where one should always adjust for the dichotomized confounder to reduce bias. We then highlight scenarios where the decision to adjust should be made more cautiously. To our knowledge, this is the first formal presentation of conditions that give information about when one should and potentially should not adjust for a dichotomized confounder.https://doi.org/10.1515/jci-2022-0047biascausal inferencedichotomized confounder62d20 |
| spellingShingle | Gabriel Erin E. Peña Jose M. Sjölander Arvid Bias attenuation results for dichotomization of a continuous confounder Journal of Causal Inference bias causal inference dichotomized confounder 62d20 |
| title | Bias attenuation results for dichotomization of a continuous confounder |
| title_full | Bias attenuation results for dichotomization of a continuous confounder |
| title_fullStr | Bias attenuation results for dichotomization of a continuous confounder |
| title_full_unstemmed | Bias attenuation results for dichotomization of a continuous confounder |
| title_short | Bias attenuation results for dichotomization of a continuous confounder |
| title_sort | bias attenuation results for dichotomization of a continuous confounder |
| topic | bias causal inference dichotomized confounder 62d20 |
| url | https://doi.org/10.1515/jci-2022-0047 |
| work_keys_str_mv | AT gabrielerine biasattenuationresultsfordichotomizationofacontinuousconfounder AT penajosem biasattenuationresultsfordichotomizationofacontinuousconfounder AT sjolanderarvid biasattenuationresultsfordichotomizationofacontinuousconfounder |