Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2409.12928 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910612675624960 |
|---|---|
| author | Zhang, Jeffrey Lee, Junu |
| author_facet | Zhang, Jeffrey Lee, Junu |
| contents | In real-world studies, the collected confounders may suffer from measurement error. Although mismeasurement of confounders is typically unintentional -- originating from sources such as human oversight or imprecise machinery -- deliberate mismeasurement also occurs and is becoming increasingly more common. For example, in the 2020 U.S. Census, noise was added to measurements to assuage privacy concerns. Sensitive variables such as income or age are oftentimes partially censored and are only known up to a range of values. In such settings, obtaining valid estimates of the causal effect of a binary treatment can be impossible, as mismeasurement of confounders constitutes a violation of the no unmeasured confounding assumption. A natural question is whether the common practice of simply adjusting for the mismeasured confounder is justifiable. In this article, we answer this question in the affirmative and demonstrate that in many realistic scenarios not covered by previous literature, adjusting for the mismeasured confounders reduces bias compared to not adjusting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_12928 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A general condition for bias attenuation by a nondifferentially mismeasured confounder Zhang, Jeffrey Lee, Junu Methodology In real-world studies, the collected confounders may suffer from measurement error. Although mismeasurement of confounders is typically unintentional -- originating from sources such as human oversight or imprecise machinery -- deliberate mismeasurement also occurs and is becoming increasingly more common. For example, in the 2020 U.S. Census, noise was added to measurements to assuage privacy concerns. Sensitive variables such as income or age are oftentimes partially censored and are only known up to a range of values. In such settings, obtaining valid estimates of the causal effect of a binary treatment can be impossible, as mismeasurement of confounders constitutes a violation of the no unmeasured confounding assumption. A natural question is whether the common practice of simply adjusting for the mismeasured confounder is justifiable. In this article, we answer this question in the affirmative and demonstrate that in many realistic scenarios not covered by previous literature, adjusting for the mismeasured confounders reduces bias compared to not adjusting. |
| title | A general condition for bias attenuation by a nondifferentially mismeasured confounder |
| topic | Methodology |
| url | https://arxiv.org/abs/2409.12928 |