Guido Imbens
Applied Econometrics Professor, Senior Fellow at the Stanford Institute for Economic Policy Research and Professor of Economics
Academic Appointments
-
Professor, Economics
-
Professor, Economics
-
Senior Fellow, Stanford Institute for Economic Policy Research (SIEPR)
-
Faculty Affiliate, Institute for Human-Centered Artificial Intelligence (HAI)
-
Member, Stanford Data Science
-
Faculty Director, Stanford Causal Science Center
2024-25 Courses
- Causality, Decision Making and Data Science
BUSGEN 108 (Aut) - Causality, Decision Making and Data Science
CS 171, DATASCI 161, ECON 115 (Aut) - Econometrics Seminar
ECON 370 (Aut, Win, Spr) - Intermediate Econometrics III: Methods for Applied Econometrics
ECON 272 (Spr) -
Independent Studies (9)
- Directed Reading
ECON 139D (Aut, Win, Spr) - Directed Reading
ECON 239D (Aut, Win, Spr, Sum) - Directed Reading in Education
EDUC 180 (Aut, Win, Spr, Sum) - Doctoral Practicum in Research
MGTECON 699 (Aut, Win, Spr, Sum) - Doctoral Practicum in Teaching
MGTECON 698 (Aut, Win, Spr, Sum) - Honors Thesis Research
ECON 199D (Aut, Win, Spr, Sum) - Individual Research
GSBGEN 390 (Aut, Win, Spr) - PhD Directed Reading
ACCT 691, FINANCE 691, MGTECON 691, MKTG 691, OB 691, OIT 691, POLECON 691 (Aut, Win, Spr, Sum) - Practical Training
ECON 299 (Aut, Win, Spr, Sum)
- Directed Reading
-
Prior Year Courses
2023-24 Courses
- Data Science for Environmental Business
ECON 185 (Spr) - Data Science for Environmental Business
MGTECON 340 (Spr) - Data Science for Environmental Business
PUBLPOL 185, SUSTAIN 135, SUSTAIN 235 (Spr) - Econometrics Seminar
ECON 370 (Aut, Win, Spr) - Intermediate Econometrics III: Methods for Applied Econometrics
ECON 272 (Spr) - Methods for Applied Econometrics
MGTECON 607 (Spr) - Quantitative Methods for Empirical Research
ECON 292 (Aut) - Quantitative Methods for Empirical Research
MGTECON 640 (Aut)
2022-23 Courses
- Data Science and Experimentation for Decision Making
MGTECON 540 (Spr) - Econometrics Workshop
ECON 370 (Aut, Win, Spr) - Intermediate Econometrics III: Methods for Applied Econometrics
ECON 272 (Spr) - Methods for Applied Econometrics
MGTECON 607 (Spr)
2021-22 Courses
- Econometrics Workshop
ECON 370 (Aut, Win, Spr) - Intermediate Econometrics III: Methods for Applied Econometrics
ECON 272 (Spr) - Methods for Applied Econometrics
MGTECON 607 (Spr)
- Data Science for Environmental Business
Stanford Advisees
-
Doctoral Dissertation Reader (AC)
Merrill Warnick -
Postdoctoral Faculty Sponsor
David Bruns-Smith, Ambarish Chattopadhyay, Kevin Chen, Jonas Metzger -
Doctoral Dissertation Advisor (AC)
Lea Bottmer, David Ritzwoller, Ravi Sojitra, Amar Venugopal, Jason Weitze, Parker Zhao -
Doctoral Dissertation Co-Advisor (AC)
Brad Ross -
Undergraduate Major Advisor
Nathan Lam -
Doctoral (Program)
Justin Young
All Publications
-
Using Wasserstein Generative Adversarial Networks for the design of Monte Carlo simulations☆
JOURNAL OF ECONOMETRICS
2024; 240 (2)
View details for DOI 10.1016/j.jeconom.2020.09.013
View details for Web of Science ID 001222944300001
-
Whitney Newey's contributions to econometrics
JOURNAL OF ECONOMETRICS
2024; 240 (2)
View details for DOI 10.1016/j.jeconom.2024.105688
View details for Web of Science ID 001222898200001
-
A New Look at P Values for Randomized Clinical Trials.
NEJM evidence
2024; 3 (1): EVIDoa2300003
Abstract
A New Look at P Values for Randomized Clinical TrialsUsing the primary results of 23,551 randomized clinical trials from the Cochrane Database, van Zwet et al. provide an empirical guide for the interpretation of an observed P value from a "typical" clinical trial in terms of the degree of overestimation of the reported effect, the probability of the effect's sign being wrong, and the predictive power of the trial.
View details for DOI 10.1056/EVIDoa2300003
View details for PubMedID 38320512
-
Optimal Experimental Design for Staggered Rollouts
MANAGEMENT SCIENCE
2023
View details for DOI 10.1287/mnsc.2023.4928
View details for Web of Science ID 001126299600001
-
A Design-Based Perspective on Synthetic Control Methods
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
2023
View details for DOI 10.1080/07350015.2023.2238788
View details for Web of Science ID 001068093700001
-
Fixed Effects and the Generalized Mundlak Estimator
REVIEW OF ECONOMIC STUDIES
2023
View details for DOI 10.1093/restud/rdad089
View details for Web of Science ID 001186710900001
-
Experimental Design in Marketplaces
STATISTICAL SCIENCE
2023; 38 (3): 458-476
View details for DOI 10.1214/23-STS883
View details for Web of Science ID 001055135300005
-
Semi-parametric estimation of treatment effects in randomised experiments
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
2023
View details for DOI 10.1093/jrsssb/qkad072
View details for Web of Science ID 001033152400001
-
Causality in Econometrics: Choice vs Chance
ECONOMETRICA
2022; 90 (6): 2541-2566
View details for DOI 10.3982/ECTA21204
View details for Web of Science ID 000888233800003
-
When Should You Adjust Standard Errors for Clustering?*
QUARTERLY JOURNAL OF ECONOMICS
2022
View details for DOI 10.1093/qje/qjac038
View details for Web of Science ID 000885663500001
-
Comment on: "Confidence Intervals for Nonparametric Empirical Bayes Analysis" by Ignatiadis and Wager
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
2022; 117 (539): 1181-1182
View details for DOI 10.1080/01621459.2022.2102501
View details for Web of Science ID 000863296200016
-
Doubly robust identification for causal panel data models
ECONOMETRICS JOURNAL
2022
View details for DOI 10.1093/ectj/utac019
View details for Web of Science ID 000839373100001
-
Bayesian Meta-Prior Learning Using Empirical Bayes
MANAGEMENT SCIENCE
2022; 68 (3): 1737-1755
View details for DOI 10.1287/mnsc.2021.4136
View details for Web of Science ID 000773344300009
-
Design-based analysis in Difference-In-Differences settings with staggered adoption
JOURNAL OF ECONOMETRICS
2022; 226 (1): 62-79
View details for DOI 10.1016/j.jeconom.2020.10.012
View details for Web of Science ID 000729637300004
-
Synthetic Difference-in-Differences
AMERICAN ECONOMIC REVIEW
2021; 111 (12): 4088-4118
View details for DOI 10.1257/aer.20190159
View details for Web of Science ID 000725477700008
-
THE ET INTERVIEW: PROFESSOR GARY CHAMBERLAIN
ECONOMETRIC THEORY
2021
View details for DOI 10.1017/S0266466621000372
View details for Web of Science ID 000763196600001
-
Statistical Significance, p-Values, and the Reporting of Uncertainty
JOURNAL OF ECONOMIC PERSPECTIVES
2021; 35 (3): 157-173
View details for DOI 10.1257/jep.35.3.157
View details for Web of Science ID 000679255600008
-
A CAUSAL BOOTSTRAP
ANNALS OF STATISTICS
2021; 49 (3): 1460-1488
View details for DOI 10.1214/20-AOS2009
View details for Web of Science ID 000684378300009
-
Matrix Completion Methods for Causal Panel Data Models
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
2021
View details for DOI 10.1080/01621459.2021.1891924
View details for Web of Science ID 000648806000001
-
Potential Outcome and Directed Acyclic Graph Approaches to Causality: Relevance for Empirical Practice in Economics
JOURNAL OF ECONOMIC LITERATURE
2020; 58 (4): 1129–79
View details for DOI 10.1257/jel.20191597
View details for Web of Science ID 000597277400004
-
Identification and Efficiency Bounds for the Average Match Function Under Conditionally Exogenous Matching
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
2020; 38 (2): 303–16
View details for DOI 10.1080/07350015.2018.1497509
View details for Web of Science ID 000607372200006
-
SAMPLING-BASED VERSUS DESIGN-BASED UNCERTAINTY IN REGRESSION ANALYSIS
ECONOMETRICA
2020; 88 (1): 265–96
View details for DOI 10.3982/ECTA12675
View details for Web of Science ID 000534143500008
-
Comment on: "The Blessings of Multiple Causes" by Yixin Wang and David M. Blei
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
2019; 114 (528): 1602–4
View details for DOI 10.1080/01621459.2019.1691008
View details for Web of Science ID 000505405600014
-
Why High-Order Polynomials Should Not Be Used in Regression Discontinuity Designs
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
2019; 37 (3): 447–56
View details for DOI 10.1080/07350015.2017.1366909
View details for Web of Science ID 000472198400006
-
Optimized Regression Discontinuity Designs
REVIEW OF ECONOMICS AND STATISTICS
2019; 101 (2): 264–78
View details for DOI 10.1162/rest_a_00793
View details for Web of Science ID 000467879400005
-
External Validity in Fuzzy Regression Discontinuity Designs
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
2019
View details for DOI 10.1080/07350015.2018.1546590
View details for Web of Science ID 000467124200001
-
Balanced Linear Contextual Bandits
ASSOC ADVANCEMENT ARTIFICIAL INTELLIGENCE. 2019: 3445–53
View details for Web of Science ID 000485292603057
-
Machine Learning Methods That Economists Should Know About
ANNUAL REVIEW OF ECONOMICS, VOL 11, 2019
2019; 11: 685–725
View details for DOI 10.1146/annurev-economics-080217-053433
View details for Web of Science ID 000483866000026
-
Pharmacogenetic testing among patients with mood and anxiety disorders is associated with decreased utilization and cost: A propensity-score matched study
DEPRESSION AND ANXIETY
2018; 35 (10): 946–52
Abstract
Naturalistic and small randomized trials have suggested that pharmacogenetic testing may improve treatment outcomes in depression, but its cost-effectiveness is not known. There is growing enthusiasm for personalized medicine, relying on genetic variation as a contributor to heterogeneity of treatment effects. We sought to examine the relationship between a commercial pharmacogenetic test for psychotropic medications and 6-month cost of care and utilization in a large commercial health plan.We performed a propensity-score matched case-control analysis of longitudinal health claims data from a large US insurer. Individuals with a mood or anxiety disorder diagnosis (N = 817) who received genetic testing for pharmacokinetic and pharmacodynamic variation were matched to 2,745 individuals who did not receive such testing. Outcomes included number of outpatient visits, inpatient hospitalizations, emergency room visits, and prescriptions, as well as associated costs over 6 months.On average, individuals who underwent testing experienced 40% fewer all-cause emergency room visits (mean difference 0.13 visits; P < 0.0001) and 58% fewer inpatient all-cause hospitalizations (mean difference 0.10 visits; P < 0.0001) than individuals in the control group. The two groups did not differ significantly in number of psychotropic medications prescribed or mood-disorder related hospitalizations. Overall 6-month costs were estimated to be $1,948 (SE 611) lower in the tested group.Pharmacogenetic testing represents a promising strategy to reduce costs and utilization among patients with mood and anxiety disorders.
View details for PubMedID 29734486
-
Approximate residual balancing: debiased inference of average treatment effects in high dimensions
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
2018; 80 (4): 597–623
View details for DOI 10.1111/rssb.12268
View details for Web of Science ID 000442217900001
-
Comments on understanding and misunderstanding randomized controlled trials: A commentary on Cartwright and Deaton.
Social science & medicine (1982)
2018
View details for PubMedID 29735351
-
Addressing unmeasured confounding in comparative observational research
PHARMACOEPIDEMIOLOGY AND DRUG SAFETY
2018; 27 (4): 373–82
Abstract
Observational pharmacoepidemiological studies can provide valuable information on the effectiveness or safety of interventions in the real world, but one major challenge is the existence of unmeasured confounder(s). While many analytical methods have been developed for dealing with this challenge, they appear under-utilized, perhaps due to the complexity and varied requirements for implementation. Thus, there is an unmet need to improve understanding the appropriate course of action to address unmeasured confounding under a variety of research scenarios.We implemented a stepwise search strategy to find articles discussing the assessment of unmeasured confounding in electronic literature databases. Identified publications were reviewed and characterized by the applicable research settings and information requirements required for implementing each method. We further used this information to develop a best practice recommendation to help guide the selection of appropriate analytical methods for assessing the potential impact of unmeasured confounding.Over 100 papers were reviewed, and 15 methods were identified. We used a flowchart to illustrate the best practice recommendation which was driven by 2 critical components: (1) availability of information on the unmeasured confounders; and (2) goals of the unmeasured confounding assessment. Key factors for implementation of each method were summarized in a checklist to provide further assistance to researchers for implementing these methods.When assessing comparative effectiveness or safety in observational research, the impact of unmeasured confounding should not be ignored. Instead, we suggest quantitatively evaluating the impact of unmeasured confounding and provided a best practice recommendation for selecting appropriate analytical methods.
View details for PubMedID 29383840
-
Exact p-Values for Network Interference
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
2018; 113 (521): 230–40
View details for DOI 10.1080/01621459.2016.1241178
View details for Web of Science ID 000438960500026
-
Redefine statistical significance.
Nature human behaviour
2018; 2 (1): 6-10
View details for DOI 10.1038/s41562-017-0189-z
View details for PubMedID 30980045
-
Redefine statistical significance
NATURE HUMAN BEHAVIOUR
2018; 2 (1): 6–10
View details for DOI 10.1038/s41562-017-0189-z
View details for Web of Science ID 000428754400005
-
Propensity Score Matching and Subclassification in Observational Studies with Multi-Level Treatments
BIOMETRICS
2016; 72 (4): 1055-1065
Abstract
In this article, we develop new methods for estimating average treatment effects in observational studies, in settings with more than two treatment levels, assuming unconfoundedness given pretreatment variables. We emphasize propensity score subclassification and matching methods which have been among the most popular methods in the binary treatment literature. Whereas the literature has suggested that these particular propensity-based methods do not naturally extend to the multi-level treatment case, we show, using the concept of weak unconfoundedness and the notion of the generalized propensity score, that adjusting for a scalar function of the pretreatment variables removes all biases associated with observed pretreatment variables. We apply the proposed methods to an analysis of the effect of treatments for fibromyalgia. We also carry out a simulation study to assess the finite sample performance of the methods relative to previously proposed methods.
View details for DOI 10.1111/biom.12505
View details for Web of Science ID 000391932100005
View details for PubMedID 26991040
-
Robust Standard Errors in Small Samples: Some Practical Advice
REVIEW OF ECONOMICS AND STATISTICS
2016; 98 (4): 701-712
View details for DOI 10.1162/REST_a_00552
View details for Web of Science ID 000385433900006
-
Recursive partitioning for heterogeneous causal effects
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA
2016; 113 (27): 7353-7360
Abstract
In this paper we propose methods for estimating heterogeneity in causal effects in experimental and observational studies and for conducting hypothesis tests about the magnitude of differences in treatment effects across subsets of the population. We provide a data-driven approach to partition the data into subpopulations that differ in the magnitude of their treatment effects. The approach enables the construction of valid confidence intervals for treatment effects, even with many covariates relative to the sample size, and without "sparsity" assumptions. We propose an "honest" approach to estimation, whereby one sample is used to construct the partition and another to estimate treatment effects for each subpopulation. Our approach builds on regression tree methods, modified to optimize for goodness of fit in treatment effects and to account for honest estimation. Our model selection criterion anticipates that bias will be eliminated by honest estimation and also accounts for the effect of making additional splits on the variance of treatment effect estimates within each subpopulation. We address the challenge that the "ground truth" for a causal effect is not observed for any individual unit, so that standard approaches to cross-validation must be modified. Through a simulation study, we show that for our preferred method honest estimation results in nominal coverage for 90% confidence intervals, whereas coverage ranges between 74% and 84% for nonhonest approaches. Honest estimation requires estimating the model with a smaller sample size; the cost in terms of mean squared error of treatment effects for our preferred method ranges between 7-22%.
View details for DOI 10.1073/pnas.1510489113
View details for Web of Science ID 000379021700039
View details for PubMedID 27382149
View details for PubMedCentralID PMC4941430
-
Matching on the Estimated Propensity Score
ECONOMETRICA
2016; 84 (2): 781-807
View details for DOI 10.3982/ECTA11293
View details for Web of Science ID 000373024100008
-
Identification and Inference With Many Invalid Instruments
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
2015; 33 (4): 474-484
View details for DOI 10.1080/07350015.2014.978175
View details for Web of Science ID 000363663200002
-
A Measure of Robustness to Misspecification
AMERICAN ECONOMIC REVIEW
2015; 105 (5): 476-480
View details for DOI 10.1257/aer.p20151020
View details for Web of Science ID 000357929400089
-
Matching Methods in Practice Three Examples
JOURNAL OF HUMAN RESOURCES
2015; 50 (2): 373-419
View details for Web of Science ID 000353933800003
-
Inference for Misspecified Models With Fixed Regressors
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
2014; 109 (508): 1601-1614
View details for DOI 10.1080/01621459.2014.928218
View details for Web of Science ID 000346797000022
-
Rejoinder
STATISTICAL SCIENCE
2014; 29 (3): 375-379
View details for DOI 10.1214/14-STS496
View details for Web of Science ID 000342603200006
-
Instrumental Variables: An Econometrician's Perspective
STATISTICAL SCIENCE
2014; 29 (3): 323-358
View details for DOI 10.1214/14-STS480
View details for Web of Science ID 000342603200001
-
Complementarity and aggregate implications of assortative matching: A nonparametric analysis
QUANTITATIVE ECONOMICS
2014; 5 (1): 29-66
View details for DOI 10.3982/QE45
View details for Web of Science ID 000334344800002
-
Social Networks and the Identification of Peer Effects
JOURNAL OF BUSINESS & ECONOMIC STATISTICS
2013; 31 (3): 253-264
View details for DOI 10.1080/07350015.2013.801251
View details for Web of Science ID 000322161800001
-
Identification and inference in nonlinear difference-in-differences models
ECONOMETRICA
2006; 74 (2): 431-497
View details for Web of Science ID 000235876700004