Abstract
A substantial body of applied statistical and econometric analysis in regional science and geography deals with data collected for aggregate spatial units of observation. These data are typically affected by a variety of measurement problems, resulting in spatial dependence and spatial heterogeneity. However, most of the empirical work fails to take this into account. In this paper we address the issue of the extent to which spatial effects matter in applied regression analysis. An overview of the formal methodological problems is given, and related to the literature in spatial statistics and spatial econometrics. -Authors
| Original language | English (US) |
|---|---|
| Title of host publication | Papers - Regional Science Association |
| Pages | 11-34 |
| Number of pages | 24 |
| Volume | 65 |
| State | Published - 1988 |
| Externally published | Yes |
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Environmental Science(all)
Fingerprint Dive into the research topics of 'Do spatial effects really matter in regression analysis?'. Together they form a unique fingerprint.
Cite this
Anselin, L., & Griffith, D. A. (1988). Do spatial effects really matter in regression analysis? In Papers - Regional Science Association (Vol. 65, pp. 11-34)