2021/09/19 by Joel A. Middleton, Middleton, Joel A.
Decision Sciences · Mathematics · #Econometrics (econ.EM) #FOS: Computer and information sciences #FOS: Economics and business #Methodology (stat.ME) #Optimal Experimental Design Methods #Statistical Methods and Bayesian Inference #Statistical Methods and Inference
paper · pdf · doi:10.48550/arxiv.2109.09220
openalex publication_date 2021/09/19 · openalex created_date 2021/09/27 · openalex updated_date 2026/07/28
This paper provides a design-based framework for variance (bound) estimation\nin experimental analysis. Results are applicable to virtually any combination\nof experimental design, linear estimator (e.g., difference-in-means, OLS, WLS)\nand variance bound, allowing for unified treatment and a basis for systematic\nstudy and comparison of designs using matrix spectral analysis. A proposed\nvariance estimator reproduces Eicker-Huber-White (aka. "robust",\n"heteroskedastic consistent", "sandwich", "White", "Huber-White", "HC", etc.)\nstandard errors and "cluster-robust" standard errors as special cases. While\npast work has shown algebraic equivalences between design-based and the\nso-called "robust" standard errors under some designs, this paper motivates\nthem for a wide array of design-estimator-bound triplets. In so doing, it\nprovides a clearer and more general motivation for variance estimators.\n