Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/246498 
Authors: 
Year of Publication: 
2021
Series/Report no.: 
UCD Centre for Economic Research Working Paper Series No. WP21/25
Version Description: 
November 2021 - Revised version of WP21/24
Publisher: 
University College Dublin, UCD School of Economics, Dublin
Abstract: 
Historical persistence studies and other regressions using spatial data commonly return severely inflated t statistics, and different standard error estimates that attempt to correct for this vary so widely as to be as to be of limited use in practice. This paper proposes a simple randomization inference procedure where the significance level of an explanatory variable is measured by its ability to outperform synthetic noise with the same estimated spatial structure. Spatial noise, in other words, acts as a treatment randomization in an artificial experiment based on correlated observational data. Examining twenty persistence studies, few perform substantially above the level of spatial noise
Document Type: 
Working Paper

Files in This Item:
File
Size
948.79 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.