Spatial interdependence and instrumental variable models

View Researcher's Other Codes

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Authors Timm Betz, Scott J. Cook, Florian Max Benjamin Hollenbach
Paper Category
Paper Abstract Instrumental variable (IV) methods are widely used to address endogeneity concerns in research using observational data. Yet, a specific kind of endogeneity – spatial interdependence – is regularly ignored in this research, threatening claims of causal identification. We show that ignoring spatial interdependence results in asymptotically biased estimates, even when instruments are randomly assigned. The extent of this bias increases when the instrument is also spatially distributed, which is the case for most widely-used instruments (such as rainfall, natural disasters, economic shocks, regionallyor globally-weighted averages, etc.). We demonstrate the extent of these biases both analytically and via Monte Carlo simulation. Finally, we discuss a simple estimation strategy that can be employed to recover consistent estimates of the desired effects.
Date of publication 2019
Code Programming Language R

Copyright Researcher 2022