Abstract
In finding effects of a binary treatment, practitioners use mostly either propensity score matching (PSM) or inverse probability weighting (IPW). However, many new treatment effect estimators are available now using propensity score and "prognostic score", and some of these estimators are much better than PSM and IPW in several aspects. In this paper, we review those recent treatment effect estimators to show how they are related to one another, and why they are better than PSM and IPW. We compare 26 estimators in total through extensive simulation and empirical studies. Based on these, we recommend recent treatment effect estimators using "overlap weight", and "targeted MLE"using statistical/machine learning, as well as a simple regression imputation/adjustment estimator using linear prognostic score models.
| Original language | English |
|---|---|
| Pages (from-to) | 357-380 |
| Number of pages | 24 |
| Journal | International Journal of Biostatistics |
| Volume | 18 |
| Issue number | 2 |
| DOIs | |
| Publication status | Published - 2022 Nov 1 |
Bibliographical note
Funding Information:Research funding: The research of Myoung-jae Lee has been supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. 2020R1A2C1A01007786), and by a Korea University fund.
Publisher Copyright:
© 2022 Walter de Gruyter GmbH, Berlin/Boston.
Keywords
- complete pairing
- inverse probability weighting
- matching
- prognostic score
- propensity score
- regression imputation/adjustment
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
Fingerprint
Dive into the research topics of 'Review and comparison of treatment effect estimators using propensity and prognostic scores'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS