EconBase
← All papers

Double/Debiased Machine Learning for Dynamic Treatment Effects via g-Estimation

Greg Lewis, Vasilis Syrgkanis

arXiv 17 Feb 2020 · Econometrics · 8 citations (OpenAlex)

arXiv:2002.07285 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We consider the estimation of treatment effects in settings when multiple treatments are assigned over time and treatments can have a causal effect on future outcomes or the state of the treated unit. We propose an extension of the double/debiased machine learning framework to estimate the dynamic effects of treatments, which can be viewed as a Neyman orthogonal (locally robust) cross-fitted version of $g$-estimation in the dynamic treatment regime. Our method applies to a general class of non-linear dynamic treatment models known as Structural Nested Mean Models and allows the use of machine learning methods to control for potentially high dimensional state variables, subject to a mean square error guarantee, while still allowing parametric estimation and construction of confidence intervals for the structural parameters of interest. These structural parameters can be used for off-policy evaluation of any target dynamic policy at parametric rates, subject to semi-parametric restrictions on the data generating process. Our work is based on a recursive peeling process, typical in $g$-estimation, and formulates a strongly convex objective at each stage, which allows us to extend the $g$-estimation framework in multiple directions: i) to provide finite sample guarantees, ii) to estimate non-linear effect heterogeneity with respect to fixed unit characteristics, within arbitrary function spaces, enabling a dynamic analogue of the RLearner algorithm for heterogeneous effects, iii) to allow for high-dimensional sparse parameterizations of the target structural functions, enabling automated model selection via a recursive lasso algorithm. We also provide guarantees for data stemming from a single treated unit over a long horizon and under stationarity conditions.

Citation extraction

48
references
85
in-text mentions
48
distinct cited
3
self-citations
17,391
main-text words

appendix boundary found by appendix_command · 52% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Victor Chernozhukov, Denis Chetverikov, Mert Demirer, Esther Duflo,… (2018) Double/debiased machine learning for treatment and structural parameters0.92810580%
2James M. Robins (2004) Optimal Structural Nested Models for Optimal Sequential Decisions, pages 189–3260.87482100%
3Miguel A Hernán and James M Robins (2010) Causal inference: What if, 20100.81142100%
4Dylan J Foster and Vasilis Syrgkanis (2019) Orthogonal statistical learning self0.7373367%
5Bibhas Chakraborty and Erica E. M. Moodie (2013) Semi-parametric Estimation of Optimal DTRs by Modeling Contrasts of Conditional Mean Outcomes, pages 53–780.73732100%
6James M Robins (1994) Correcting for non-compliance in randomized trials using structural nested mean models0.73732100%
7Peter M Robinson (1988) Root-n-consistent semiparametric regression0.73732100%
8Stijn Vansteelandt, Marshall Joffe, et al (2014) Structural nested models and g-estimation: the partially realized promise0.73732100%
9Chunrong Ai and Xiaohong Chen (2003) Efficient estimation of models with conditional moment restrictions containing unknown functions0.64422100%
10Victor Chernozhukov, Juan Carlos Escanciano, Hidehiko Ichimura, Whit… Locally Robust Semiparametric Estimation0.64422100%

Showing the top 10 of 48 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Inference on Optimal Dynamic Policies via Softmax Approximation0.84333
2Dynamic covariate balancing: estimating treatment effects over time with potential local projections0.51121
3Automatic Debiased Machine Learning for Dynamic Treatment Effects and General Nested Functionals0.40511
4Synthetic Blips: Generalizing Synthetic Controls for Dynamic Treatment Effects0.40511
5Structural Analysis of Vector Autoregressive Models0.40511
6Dynamic Local Average Treatment Effects0.40511
7xtdml: Double Machine Learning Estimation to Static Panel Data Models with Fixed Effects in R0.40511