1 code implementation • 23 May 2023 • Timothy B. Armstrong, Patrick Kline, Liyang Sun
Empirical research typically involves a robustness-efficiency tradeoff.
no code implementations • 13 Oct 2022 • Timothy B. Armstrong, Martin Weidner, Andrei Zeleneev
We consider estimation and inference for a regression coefficient in panels with interactive fixed effects (i. e., with a factor structure).
no code implementations • 29 Dec 2020 • Timothy B. Armstrong, Michal Kolesár, Soonwoo Kwon
We consider inference on a scalar regression coefficient under a constraint on the magnitude of the control coefficients.
2 code implementations • 7 Apr 2020 • Timothy B. Armstrong, Michal Kolesár, Mikkel Plagborg-Møller
We construct robust empirical Bayes confidence intervals (EBCIs) in a normal means problem.
1 code implementation • 22 Aug 2018 • Timothy B. Armstrong, Michal Kolesár
We show that near-optimal confidence intervals (CIs) can be formed by taking a generalized method of moments (GMM) estimator, and adding and subtracting the standard error times a critical value that takes into account the potential bias from misspecification of the moment conditions.
Econometrics Methodology
1 code implementation • 13 Dec 2017 • Timothy B. Armstrong, Michal Kolesár
We consider estimation and inference on average treatment effects under unconfoundedness conditional on the realizations of the treatment variable and covariates.
Applications Econometrics Methodology
1 code implementation • 3 Jun 2016 • Timothy B. Armstrong, Michal Kolesár
We show that using the bandwidth that minimizes the maximum mean-squared error results in CIs that are nearly efficient and that in this case, the critical value depends only on the rate of convergence.
Applications Statistics Theory Statistics Theory
1 code implementation • 19 Nov 2015 • Timothy B. Armstrong, Michal Kolesár
When the function class is centrosymmetric, these efficiency bounds imply that minimax CIs are close to efficient at smooth regression functions.
Statistics Theory Applications Statistics Theory
1 code implementation • 30 Nov 2014 • Timothy B. Armstrong, Michal Kolesár
This paper proposes a simple adjustment that gives correct coverage in such situations: replace the normal quantile with a critical value that depends only on the kernel and ratio of the maximum and minimum bandwidths the researcher has entertained.
Applications