The Variance of Regression Coefficients When the Population Is Finite

33 Pages Posted: 28 Mar 2022

See all articles by Richard Startz

Richard Startz

UCSB

Douglas G. Steigerwald

University of California, Santa Barbara (UCSB) - Department of Economics

Multiple version iconThere are 2 versions of this paper

Date Written: January 5, 2022

Abstract

We provide general results for the asymptotic variance of regression coefficients computed
from a sample drawn from a finite population. We encompass the potential
outcomes and classic regression frameworks allowing for both heterogeneous treatment
effects and random-across-resampling shocks. Formulae are provided for the asymptotic
variances of both treatment effects and attributes. In general, the variances combine
the expected results from both frameworks.

Keywords: regression coefficients, finite population

JEL Classification: C10,C20

Suggested Citation

Startz, Richard and Steigerwald, Douglas G., The Variance of Regression Coefficients When the Population Is Finite (January 5, 2022). Available at SSRN: https://ssrn.com/abstract=4002003 or http://dx.doi.org/10.2139/ssrn.4002003

Richard Startz (Contact Author)

UCSB ( email )

Department of Economics
University of California
Santa Barbara, CA 93106-9210
United States
805-893-2895 (Phone)

Douglas G. Steigerwald

University of California, Santa Barbara (UCSB) - Department of Economics ( email )

2127 North Hall
Santa Barbara, CA 93106
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
9
Abstract Views
43
PlumX Metrics