Quasi-rerandomization for observational studies
Abstract Background In the causal analysis of observational studies, covariates should be carefully balanced to approximate a randomized experiment. Numerous covariate balancing methods have been proposed for this purpose. However, it is often unclear what type of randomized experiments the balancin...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-06-01
|
Series: | BMC Medical Research Methodology |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12874-023-01977-7 |
_version_ | 1797789726427578368 |
---|---|
author | Hengtao Zhang Wen Su Guosheng Yin |
author_facet | Hengtao Zhang Wen Su Guosheng Yin |
author_sort | Hengtao Zhang |
collection | DOAJ |
description | Abstract Background In the causal analysis of observational studies, covariates should be carefully balanced to approximate a randomized experiment. Numerous covariate balancing methods have been proposed for this purpose. However, it is often unclear what type of randomized experiments the balancing approaches aim to approximate; and this may cause ambiguity and hamper the synthesis of balancing characteristics within randomized experiments. Methods Randomized experiments based on rerandomization, known for significant improvement on covariate balance, have recently gained attention in the literature, but no attempt has been made to integrate this scheme into observational studies for improving covariate balance. Motivated by the above concerns, we propose quasi-rerandomization, a novel reweighting method, where observational covariates are rerandomized to be the anchor for reweighting such that the balanced covariates obtained from rerandomization can be reconstructed by the weighted data. Results Through extensive numerical studies, not only does our approach demonstrate similar covariate balance and comparable estimation precision of treatment effect to rerandomization in many situations, but it also exhibits advantages over other balancing techniques in inferring the treatment effect. Conclusion Our quasi-rerandomization method can approximate the rerandomized experiments well in terms of improving the covariate balance and the precision of treatment effect estimation. Furthermore, our approach shows competitive performance compared with other weighting and matching methods. The codes for the numerical studies are available at https://github.com/BobZhangHT/QReR . |
first_indexed | 2024-03-13T01:54:46Z |
format | Article |
id | doaj.art-bd273bcf682341afb74d433dc159ff6a |
institution | Directory Open Access Journal |
issn | 1471-2288 |
language | English |
last_indexed | 2024-03-13T01:54:46Z |
publishDate | 2023-06-01 |
publisher | BMC |
record_format | Article |
series | BMC Medical Research Methodology |
spelling | doaj.art-bd273bcf682341afb74d433dc159ff6a2023-07-02T11:19:14ZengBMCBMC Medical Research Methodology1471-22882023-06-0123111510.1186/s12874-023-01977-7Quasi-rerandomization for observational studiesHengtao Zhang0Wen Su1Guosheng Yin2Department of Statistics and Actuarial Science, The University of Hong KongDepartment of Statistics and Actuarial Science, The University of Hong KongDepartment of Statistics and Actuarial Science, The University of Hong KongAbstract Background In the causal analysis of observational studies, covariates should be carefully balanced to approximate a randomized experiment. Numerous covariate balancing methods have been proposed for this purpose. However, it is often unclear what type of randomized experiments the balancing approaches aim to approximate; and this may cause ambiguity and hamper the synthesis of balancing characteristics within randomized experiments. Methods Randomized experiments based on rerandomization, known for significant improvement on covariate balance, have recently gained attention in the literature, but no attempt has been made to integrate this scheme into observational studies for improving covariate balance. Motivated by the above concerns, we propose quasi-rerandomization, a novel reweighting method, where observational covariates are rerandomized to be the anchor for reweighting such that the balanced covariates obtained from rerandomization can be reconstructed by the weighted data. Results Through extensive numerical studies, not only does our approach demonstrate similar covariate balance and comparable estimation precision of treatment effect to rerandomization in many situations, but it also exhibits advantages over other balancing techniques in inferring the treatment effect. Conclusion Our quasi-rerandomization method can approximate the rerandomized experiments well in terms of improving the covariate balance and the precision of treatment effect estimation. Furthermore, our approach shows competitive performance compared with other weighting and matching methods. The codes for the numerical studies are available at https://github.com/BobZhangHT/QReR .https://doi.org/10.1186/s12874-023-01977-7Causal inferenceCovariate balanceObservational dataRerandomizationTreatment effect |
spellingShingle | Hengtao Zhang Wen Su Guosheng Yin Quasi-rerandomization for observational studies BMC Medical Research Methodology Causal inference Covariate balance Observational data Rerandomization Treatment effect |
title | Quasi-rerandomization for observational studies |
title_full | Quasi-rerandomization for observational studies |
title_fullStr | Quasi-rerandomization for observational studies |
title_full_unstemmed | Quasi-rerandomization for observational studies |
title_short | Quasi-rerandomization for observational studies |
title_sort | quasi rerandomization for observational studies |
topic | Causal inference Covariate balance Observational data Rerandomization Treatment effect |
url | https://doi.org/10.1186/s12874-023-01977-7 |
work_keys_str_mv | AT hengtaozhang quasirerandomizationforobservationalstudies AT wensu quasirerandomizationforobservationalstudies AT guoshengyin quasirerandomizationforobservationalstudies |