EconBase
← All papers

Estimation based on nearest neighbor matching: from density ratio to average treatment effect

Zhexiao Lin, Peng Ding, Fang Han

arXiv 27 Dec 2021 · Mathematics — Statistics Theory · publishedEconometrica (2023) · 4 citations (OpenAlex)

arXiv:2112.13506 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Nearest neighbor (NN) matching as a tool to align data sampled from different groups is both conceptually natural and practically well-used. In a landmark paper, Abadie and Imbens (2006) provided the first large-sample analysis of NN matching under, however, a crucial assumption that the number of NNs, $M$, is fixed. This manuscript reveals something new out of their study and shows that, once allowing $M$ to diverge with the sample size, an intrinsic statistic in their analysis actually constitutes a consistent estimator of the density ratio. Furthermore, through selecting a suitable $M$, this statistic can attain the minimax lower bound of estimation over a Lipschitz density function class. Consequently, with a diverging $M$, the NN matching provably yields a doubly robust estimator of the average treatment effect and is semiparametrically efficient if the density functions are sufficiently smooth and the outcome model is appropriately specified. It can thus be viewed as a precursor of double machine learning estimators.

Citation extraction

67
references
170
in-text mentions
67
distinct cited
3
self-citations
22,758
main-text words

appendix boundary found by appendix_command · 54% 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
1Noshad, M., Moon, K. R., Sekeh, S. Y., and Hero, A. O (2017) Direct estimation of information divergence using nearest neighbor ratios1.00083100%
2Abadie, A. and Imbens, G. W (2006) Large sample properties of matching estimators for average treatment effects0.98726596%
3Abadie, A. and Imbens, G. W (2011) Bias-corrected matching estimators for average treatment effects0.98320495%
4Abadie, A. and Imbens, G. W (2012) A martingale representation for matching estimators0.92843100%
5Chernozhukov, V., Chetverikov, D., Demirer, M., Duflo, E., Hansen, C… (2018) Double/debiased machine learning for treatment and structural parameters0.86314364%
6Kremer, J., Gieseke, F., Pedersen, K. S., and Igel, C (2015) Nearest neighbor density ratio estimation for large-scale applications in astronomy0.84333100%
7Lima, M., Cunha, C. E., Oyaizu, H., Frieman, J., Lin, H., and Sheldo… (2008) Estimating the redshift distribution of photometric galaxy samples0.84333100%
8Zhao, P. and Lai, L (2020) Minimax optimal estimation of KL divergence for continuous distributions0.84333100%
9Bang, H. and Robins, J. M (2005) Doubly robust estimation in missing data and causal inference models0.81142100%
10Hahn, J (1998) On the role of the propensity score in efficient semiparametric estimation of average treatment effects0.81142100%

Showing the top 10 of 67 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
1Nearest Neighbor Matching as Least Squares Density Ratio Estimation and Riesz Regression1.000235
2On the consistency of bootstrap for matching estimators1.000224
3On the limiting variance of matching estimators1.00063
4Bias correction for Chatterjee's graph-based correlation coefficient0.92843
5On Rosenbaum's Rank-based Matching Estimator0.87464
6Vector Search As Nearest Neighbor Matching: RAG-based Policy Learning in Causal Inference0.84343
7Post-Matching Two-Way Fixed Effects Estimation0.84333
8On regression-adjusted imputation estimators of the average treatment effect0.794247
9A Unified Framework for Debiased Machine Learning: Riesz Representer Fitting under Bregman Divergence0.69394
10On propensity score matching with a diverging number of matches0.64441