Dirty spatial econometrics

Spatial data are often contaminated with a series of imperfections that reduce their quality and can dramatically distort the inferential conclusions based on spatial econometric modeling. A “clean” ideal situation considered in standard spatial econometrics textbooks is when we fit Cliff-Ord-type models to data where the spatial units constitute the full population, there are no missing data, and there is no uncertainty on the spatial observations that are free from measurement and locational errors. Unfortunately in practical cases the reality is often very different and the datasets contain all sorts of imperfections: They are often based on a sample drawn from the whole population, some data are missing and they almost invariably contain both attribute and locational errors. This is a situation of “dirty” spatial econometric modeling. Through a series of Monte Carlo experiments, this paper considers the effects on spatial econometric model estimation and hypothesis testing of two specific sources of dirt, namely missing data and locational errors.