Spatial Econometrics for Misaligned Data

TL;DR

This paper introduces new methods for spatial regression analysis with misaligned data, enabling accurate modeling without estimating error covariances, and demonstrates their effectiveness through reanalysis of a key study.

Contribution

It develops two novel regression techniques for misaligned spatial data that do not require error covariance estimation, advancing spatial econometrics methodology.

Findings

Methods produce economically significant differences in reanalysis

Qualitative conclusions of original study are largely sustained

Provides practical tools for handling misaligned spatial data

Abstract

We produce methodology for regression analysis when the geographic locations of the independent and dependent variables do not coincide, in which case we speak of misaligned data. We develop and investigate two complementary methods for regression analysis with misaligned data that circumvent the need to estimate or specify the covariance of the regression errors. We carry out a detailed reanalysis of Maccini and Yang (2009) and find economically significant quantitative differences but sustain most qualitative conclusions.