An Introduction to the Augmented Inverse Propensity Weighted Estimator
The DOI matches its Crossref record; 33 of the 33 references it cites were found in a registry or an index.
Abstract
In this paper, we discuss an estimator for average treatment effects (ATEs) known as the augmented inverse propensity weighted (AIPW) estimator. This estimator has attractive theoretical properties and only requires practitioners to do two things they are already comfortable with: (1) specify a binary regression model for the propensity score, and (2) specify a regression model for the outcome variable. Perhaps the most interesting property of this estimator is its so-called “double robustness.” Put simply, the estimator remains consistent for the ATE if either the propensity score model or the outcome regression is misspecified but the other is properly specified. After explaining the AIPW estimator, we conduct a Monte Carlo experiment that compares the finite sample performance of the AIPW estimator to three common competitors: a regression estimator, an inverse propensity weighted (IPW) estimator, and a propensity score matching estimator. The Monte Carlo results show that the AIPW estimator has comparable or lower mean square error than the competing estimators when the propensity score and outcome models are both properly specified and, when one of the models is misspecified, the AIPW estimator is superior.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These doubly robust approaches provide consistent estimates even if one of the models—the propensity score model or the outcome regression model—is misspecified.”
Citations
Cites
The central role of the propensity score in observational studies for causal effects
ROSENBAUM, P. R., & RUBIN, D. B. (1983) · Biometrika · doi:10.1093/biomet/70.1.41 · Cited by 31,241 · cited 2×
“Furthermore, we assume that potential outcomes are defined as in Rosenbaum and Rubin (1983) such that Yi(1) is the outcome that wewould observe if unit i had received treatment and Yi(0) is the outcome that we would observe if unit i had received treatment.”
BackgroundInfluentialCausality: Models, Reasoning, and Inference
Pearl, J. (2009) · doi:10.1017/cbo9780511803161 · Cited by 11,653
CAUSALITY: MODELS, REASONING AND INFERENCE
Hitchcock, C. (2001) · The Philosophical Review · doi:10.1215/00318108-110-4-639 · Cited by 4,741
Identification of Causal Effects Using Instrumental Variables
Angrist, J. D., Imbens, G. W., & Rubin, D. B. (1996) · Journal of the American Statistical Association · doi:10.1080/01621459.1996.10476902 · Cited by 4,230
Matching as Nonparametric Preprocessing for Reducing Model Dependence in Parametric Causal Inference
Ho, D. E., Imai, K., King, G., & Stuart, E. A. (2007) · Political Analysis · doi:10.1093/pan/mpl013 · Cited by 4,205 · cited 1×
“2 for a proof of this result and see Ho et al. (2007) for a related but distinct estimator that has this double robustness property.”
BackgroundHastie, T., & Tibshirani, R. (1986) · Statistical Science · doi:10.1214/ss/1177013604 · Cited by 3,409
Nonparametric Estimation of Average Treatment Effects Under Exogeneity: A Review
Imbens, G. W. (2004) · Review of Economics and Statistics · doi:10.1162/003465304323023651 · Cited by 2,994
Causality: models, reasoning, and inference
(2000) · Choice Reviews Online · doi:10.5860/choice.38-1494a · Cited by 2,873
Estimation of Regression Coefficients When Some Regressors are not Always Observed
Robins, J. M., Rotnitzky, A., & Zhao, L. P. (1994) · Journal of the American Statistical Association · doi:10.1080/01621459.1994.10476818 · Cited by 2,823 · cited 2×
“See Rubin (2006) for a book length treatment on matching, or Diamond and Sekhon (2005) and Ho et al.”
BackgroundRobins, J. (1986) · Mathematical Modelling · doi:10.1016/0270-0255(86)90088-6 · Cited by 2,451 · cited 2×
“Given the stated assumptions of this paper, it has been shown that such a model can be used to identify the ATE through a subclassification adjustment (Cochran 1968), the g-functional (Robins 1986), or the backdoor adjustment (Pearl 1995, 2000).”
BackgroundMethodInfluential
Research works printed but not linked: 4
- Busso, 2009a, Finite sample properties of semiparametric estimators of average treatment effects
- Sekhon, 2009, Multivariate and propensity score matching with balance optimization
- 2007, R: A language and environment for statistical computing
- Robins James M. 1999. Robust estimation in sequentially ignorable missing data and causal inference models. Proceedings of the American Statistical Association Section on Bayesian Statistical Science 6–10.
Cited by
Items 301–375 of 375
Scott, T. A. (2014) · SSRN Electronic Journal · doi:10.2139/ssrn.2519663
Was Civil War surgery effective?
Baker, M. J. (2018) · Historical Methods A Journal of Quantitative and Interdisciplinary History · doi:10.1080/01615440.2017.1408440
Pontines, V. C. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3144114
“11 See Lunceford and Davidian (2004) and Glynn and Quinn (2010) in the case of binary treatments, while Zhang et al. (2016) in the case of continuous treatments.”
An OLS-Based Method for Causal Inference in Observational Studies
Xu, Y. (2019) · IUScholarWorks (Indiana University) · doi:10.7912/c2/2804
Kreif, N. (2013) · LSHTM Research Online (London School of Hygiene and Tropical Medicine) · doi:10.17037/pubs.04653719
Machine Learning Methods for Causal Inference with Observational Biomedical Data
Averitt, A. (2020) · doi:10.7916/d8-je06-eh12 · Cited by 1
Causal Inference with Missingness in Confounders
Bagmar, M. S. H. (2019) · doi:10.11575/prism/36819
Estimating average treatment effect on the treated via sufficient dimension reduction
Li, L., Luo, W., Wen, X. M., & Yu, Z. (2021) · Stat · doi:10.1002/sta4.367
“…literature to esti- mate τ, including the outcome regression (OR Hahn, 1998; Luo et al. 2017), inverse probability weighting (IPW Han & Kim, 2011; Hirano et al. 2003), and the augmented inverse propensity weighting estimator (AIPW Glynn & Quinn, 2010; Ma et al. 2019; Robins et al. 1994; Tan, 2010).”
BackgroundMethodBaker, S. E., Monlezun, D. J., Wieghard, N., Whitlow, C. B., & Margolin, D. A. (2021) · Surgical Endoscopy · doi:10.1007/s00464-021-08403-3
Doubly Robust Estimation with Machine Learning PredictionsPreprint
Rostami, M., Saarela, O., & Escobar, M. D. (2021) · arXiv (Cornell University)
The effectiveness of currency intervention: Evidence from Mongolia
Pontines, V. C., Luvsannyam, D., Atarbaatar, E., & Munkhtsetseg, U. (2021) · Journal of International Financial Markets Institutions and Money · doi:10.1016/j.intfin.2021.101439
Palomero, M. L. (1998) · Apunts Educación Física y Deportes
Loh, W. W., & Ren, D. (2021) · PsyArXiv (OSF Preprints) · doi:10.31234/osf.io/zkdqa
Loh, W. W., & Ren, D. (2021) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/yve6u
Samwini, C. J. B., Ratna, N. N., & Bigsby, H. R. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4135750
Working During College: Stumbling Block or Stepping-Stone?
Witteveen, D. (2019) · American Educational Research Association Annual Meeting (AERA) · doi:10.3102/1433532
Langen, H. (2022) · doi:10.51363/unifr.eth.2022.004
Zhou, Y., & Song, P. X. ‐. (2023) · Statistics in Medicine · doi:10.1002/sim.9766
Overview of estimating the average treatment effect using dimension reduction methods
Kim, M. J. (2023) · Korean Journal of Applied Statistics · doi:10.5351/kjas.2023.36.4.323
Pincombe, A., Mittinty, M., & Karnon, J. D. (2023) · Healthcare Analytics · doi:10.1016/j.health.2023.100250 · Cited by 1
Jet Lag Does Not Impact Football Performance: Using Randomization Inference to Handle ComplexityPreprint
Tenan, M. S., Rezai, A. R., & Vigotsky, A. D. (2023) · medRxiv · doi:10.1101/2023.10.19.23296960
From Paychecks to Plates: Tracing the Impact of Layoffs on Food Access in the United StatesPreprint
Le, K., Nguyen, T. D., & Rutledge, N. (2023) · Research Square · doi:10.21203/rs.3.rs-3800833/v1
Physical performance in daily life and sports: bridging the data analytics gap
Dijkhuis, T. B. (2024) · University of Groningen research database (University of Groningen / Centre for Information Technology) · doi:10.33612/diss.867738847
Deep Learning With DAGsPreprint
Bagil, S., Daoud, A., Pena, J. M., Wodtke, G. T., & Zhou, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4698386
“These estimators include targeted maximum likelihood, augmented inverse probability weighting, and other related approaches based on the efficient influence curve (Glynn and Quinn, 2010; Van Der Laan and Rubin, 2006; Zhou, 2022).”
Grecov, P., Ackermann, K., & Bergmeir, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4830726
Information content and consensus effect of fiscal plans
Columbano, C., & Bafundi, A. (2024) · Estudios económicos · doi:10.52292/j.estudecon.2025.4154
Cross-Platforms Merger EffectsPreprint
Paudel, U. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4976777
Layers of Auditor Industry Specialization: Evidence from Client Firms’ Investment Efficiency
Choy, H., Lin, J. J., & Yeh, Y. (2024) · Journal of International Accounting Research · doi:10.2308/jiar-2023-066
The functional average treatment effect
Sparkes, S., Garcia, E., & Zhang, L. (2024) · Journal of Causal Inference · doi:10.1515/jci-2023-0076 · Cited by 2
Lee, E., & Choi, Y. (2025) · Korean Journal of Applied Statistics · doi:10.5351/kjas.2025.38.1.001
Within-trial data borrowing for sequential multiple assignment randomized trials
Kotalik, A., Vock, D. M., Sherwood, N. E., Hobbs, B. P., & Koopmeiners, J. S. (2024) · Biostatistics · doi:10.1093/biostatistics/kxaf003
Yue, L., Wu, C. O., Li, G., & Li, Z. (2025) · Statistical Methods in Medical Research · doi:10.1177/09622802241313288
“Based on the estimated propensity score weights, the ATEs can be computed by using the inverse probability weighting (IPW) method 16,17 or augmented IPW method 18,19 or double robust method.”
Kouakou, K. C., & Yapo, A. R. V. (2025) · Revue française d économie · doi:10.3917/rfe.252.0009
Input Procurement: Theory and EvidencePreprint
Ponti, P. D., Gattai, V., & Natale, P. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5275820
Krakowski, K., Oliver, D., Arribas, M., Logeswaran, Y., Micheli, A. D., Patel, R., Stahl, D. R., & Fusar‐Poli, P. (2026) · Translational Psychiatry · doi:10.1038/s41398-026-03914-w · Cited by 2
“We then constructed Precision Treatment Rules (PTRs) to recommend the optimal treatment based on patients ’ baseline characteristics and preferences.”
Estimating average treatment effect using multiple imputation for handling confounder missingness
Bagmar, M. S. H., & Shen, H. (2025) · Communications in Statistics - Simulation and Computation · doi:10.1080/03610918.2025.2534890
How Did You Find Your Job? Effects of the Job Search Channels on Labour Market Outcomes in GermanyPreprint
Zaharieva, A., & Afonina, M. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5364817
Rudd, D., Wine, M. D., Pedler, R., Wright, M., Gleason, V. L., Pérez-Muñoz, A., Tuna, B., Tempchin, J., Flowers, T. A., & Bryan, C. J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5372908
Transfer Learning for Individualized Treatment Rules with Application to Sepsis Patients Data
Wang, A., Wentzlof, K., Rajala, J., Green, M., Zhang, Y., & Yang, S. (2025) · Journal of Data Science · doi:10.6339/25-jds1193
MISS: An Incomplete Tabular Data Representation System with Missing Mechanism Learning
Wu, Y., Liang, S., Qiang, L., Miao, X., Zhao, X., Cai, J., Gaol, Y., & Yin, J. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00123
“Armed with casual inference theory [51], MPS is capable of directly learning the data missing mechanism from a very small sample dataset, thereby eliminating the bias introduced by complex missing mechanisms.”
Czyżewski, B., Guth, M., Matuszczak, A., Smędzik-Ambroży, K., & Stępień, S. (2025) · International Journal of Emerging Markets · doi:10.1108/ijoem-04-2025-0702
Adaptive stratified sampling design in two-phase studies for average causal effect estimation
Zeng, M., Wang, Q., Sui, Z., Zhang, H., & Xu, J. (2025) · Biometrics · doi:10.1093/biomtc/ujaf143 · Cited by 1
The Impact of Internet Usage on Nonfarm Employment for Rural Women
Liu, W., Zhao, L., Mesak, H. I., & Hu, Z. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-95-1595-0_8
Galperín, H., Bar, F., & Penate, A. C. (2025) · Information Communication & Society · doi:10.1080/1369118x.2025.2591771
“A key advantage of AIPW is its double robustness: the estimator remains consistent if either the propensity score model or the outcome model is correctly specified (Dudík et al., 2014; Glynn & Quinn, 2010).”
The ripples of reform: Nepal’s evolving gender-based employment landscape
Shrestha, A. (2025) · Peace and Sustainability · doi:10.1016/j.nerpsj.2025.100020
Nguyen, H. V., Bornstein, S., Gamble, J.-M., Mathews, M., Bishop, L. D., & Mital, S. (2020) · Figshare · doi:10.6084/m9.figshare.12299450
Additional file 1 of An improved multiply robust estimator for the average treatment effect
Wang, C., Wei, K., Huang, C., Yu, Y., & Qin, G. (2023) · Figshare · doi:10.6084/m9.figshare.24295697
Osawa, I., Goto, T., Kudo, D., Hayakawa, M., Yamakawa, K., Kushimoto, S., Foster, D., Kellum, J. A., & Doi, K. (2023) · Figshare · doi:10.6084/m9.figshare.23557874
Loh, W. W., & Kim, J.-S. (2022) · Figshare · doi:10.6084/m9.figshare.21203346
Karimi, S., & Kluger, R. (2026) · Accident Analysis & Prevention · doi:10.1016/j.aap.2025.108380
Is there a “glass cliff” for women at the top of the corporate ladder?
Song, K., & Tian, Y. S. (2026) · Journal of Law Finance and Accounting · doi:10.1108/jlfa-02-2025-0012
Paul, A. K., & Greiner, R. (2026) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2026.104994
Han, D., Duran, C., Martines, P. W., Skinner, Harlow, A. F., Li, M., Barrington‐Trimis, J. L., Halbert, C. H., Meza, R., Levy, D. T., et al. (2026) · American Journal of Epidemiology · doi:10.1093/aje/kwag033
Behavioral Charity: Third‐Party Ratings of Nonprofits as Salience and Heuristics
Haque, A. (2026) · Public Administration Review · doi:10.1111/puar.70106
A note on cabinet’s policy orientation and gross capital inflows in OECD countries
Mavrogiannis, C., & Tagkalakis, A. (2026) · Review of World Economics · doi:10.1007/s10290-026-00632-9
Essays on Financial Crises and Growth Surges
Atsebi, B. J.-M. (2020) · theses.fr (ABES) · doi:10.70675/729cd27azb1e6z43efzb940zf06861301ac3
Three essays on innovation networks, cluster policies and regional knowledge production
N’Ghauran, K. A. (2020) · theses.fr (ABES) · doi:10.70675/be25c8dcz4132z45ecz90e6ze038e9b171f2
Hukou identity and economic behaviours : a social identity perspective
Yang, Y. (2023) · theses.fr (ABES) · doi:10.70675/717023b5z0fb6z438bz827fza1599670884f · Cited by 2
Designing Recommender Systems for the Labor Market
Bied, G. (2024) · theses.fr (ABES) · doi:10.70675/8e9b30dcz72f6z42bezb84az0ba80996a9b9 · Cited by 1
Tani, T., Ikeda, T., Nozoe, M., Kubo, H., Miyata, K., Ogino, T., Ide, K., Kimura, Y., & Fushimi, K. (2026) · Journal of the American Medical Directors Association · doi:10.1016/j.jamda.2026.106202
Prognostic Covariate Adjustment in Non-Ideal Conditions: Limitations and Doubly Robust Alternatives
Jin, M. (2026) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2026.2658628 · Cited by 1
Causal inference with randomized and quasi-experimental designs
Kwon, M., & Steiner, P. M. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-26629-4.00210-0
Doucette, M. L., Macfarlan, D. L., Kasabuski, M., Chin, J., & Fisher, E. (2026) · Psychiatry International · doi:10.3390/psychiatryint7030128 · Cited by 3
“First, we used three alternative ATE estimation methods: propensity score matching (PSM) [53,54], augmented inverse probability weighting (AIPW) [55–58], and inverse probability weighting with machine learning (IPW-ML) [59].”
Mabungane, S., Ramroop, S., & Mwambi, H. G. (2026) · South African Journal of Education · doi:10.15700/saje.v46n2a2610
Wu, Y., Yin, Y., & Ling, Y. (2026) · Journal of Biopharmaceutical Statistics · doi:10.1080/10543406.2026.2676076
Polikoff, M. S., Pardo, N., Byon, J., Saavedra, A. R., Rapaport, A., Silver, D., & Garland, M. W. (2026) · International Journal of Public Opinion Research · doi:10.1093/ijpor/edag011
Kryszak, Ł., Staniszewski, J., & Smędzik-Ambroży, K. (2026) · Agricultural and Food Economics · doi:10.1186/s40100-026-00502-w
“AIPW is considered a double-robust estimator, meaning that it yields consistent results if either the treatment model (propensity score) or the outcome model is correctly specified (Glynn and Quinn 2010).”
Subsidize rent or subsidize homeownership? Evidence from a Hong Kong experiment
Wong, M. (2026) · Regional Science and Urban Economics · doi:10.1016/j.regsciurbeco.2026.104254
Opportunity and necessity entrepreneurship and education
Dutta, N., Stivers, A., & Ammons, J. (2026) · Applied Economics Letters · doi:10.1080/13504851.2026.2712574
Kaier, K., Hazard, D., Czerny, M., Rilinger, J., Hilgendorf, I., Wolf, D., Westermann, D., Mühlen, C. V. Z., & Valina, C. M. (2026) · BMC Cardiovascular Disorders · doi:10.1186/s12872-026-06462-9
“Because this method relies on either—but not necessarily both—models being correctly specified, it is referred to as a “doubly robust” estimation technique [10–12].”
Zhao, X., Wang, R., Weng, Y.-T., & Huang, D. P. (2026) · Statistics in Biopharmaceutical Research · doi:10.1080/19466315.2026.2723440
Grootenhuis, J. G. A., Wijers, S., Hannink, G., Adbegovic, I., Herruer, J. M., Krämer, I., Hutteman, M., Ubels, S., & Klarenbeek, B. R. (2026) · Diseases of the Esophagus · doi:10.1093/dote/doag106
“20 The CCI was calculated for each patient based on all recorded Clavien–Dindo graded complications and was analyz ed as a continuous outcome in the weighted cohort to ref lect the overall postoperative complication burden.”
Zhang, Y., Zhang, W., & Guo, X. (2016) · Annals of Applied Mathematics · doi:10.4208/aam.v32.n2.p200
Metadata
- Authors
- Glynn, A. N., & Quinn, K. M.
- Affiliations
- Harvard University (US)
- University of California, Berkeley (US)
- Corresponding author
- Glynn, Adam N.
- Venue
- Political Analysis
- Publisher
- Cambridge University Press (CUP)
- Published
- 2010
- Volume
- 18
- Issue
- 1
- Pages
- 36-56
- ISSN
- 1047-1987 (ISSN-L)
- 1476-4989
- OpenAlex
- W2066443416
- Cited by
- 374
- References
- 33
- Citations by year
- 2026: 29 · 2025: 57 · 2024: 58 · 2023: 44 · 2022: 36 · 2021: 45 · 2020: 25 · 2019: 18 · 2018: 12 · 2017: 9 · 2016: 15 · 2015: 6 · 2014: 6 · 2013: 9 · 2012: 2
- FWCI
- 1.11
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Political Analysis (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Mathematics › Statistics and Probability › Advanced Causal Inference Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Clinical Trials
- Keywords
- average treatment effect, double robustness, propensity score, inverse propensity weighting, propensity score matching, model misspecification, finite sample properties, causal inference
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.