Regression analysis of spatial data

• Published in: Ecology letters Vol. 13; no. 2; pp. 246 - 264
• Main Authors: Beale, Colin M, Lennon, Jack J, Yearsley, Jon M, Brewer, Mark J, Elston, David A
• Format: Journal Article
• Language: English
• Published: Oxford, UK Oxford, UK : Blackwell Publishing Ltd 01.02.2010; Blackwell Publishing Ltd; Blackwell
• Subjects: Animal and plant ecology; Animal, plant and microbial ecology; Bayesian analysis; Biological and medical sciences; Comparative analysis; Conditional autoregressive; Ecology; Ecology - methods; Fundamental and applied biological sciences. Psychology; General aspects; generalized least squares; Geography; macroecology; Models, Biological; ordinary least squares; Regression Analysis; Research methodology; Simulation; simultaneous autoregressive; spatial analysis; spatial autocorrelation; spatial eigenvector analysis; simultaneous autoregressive; spatial eigenvector analysis; Macroecology; Spatial analysis; spatial autocorrelation; generalized least squares; ordinary least squares; Regression analysis; Autocorrelation; Conditional autoregressive
• ISSN: 1461-023X; 1461-0248
• DOI: 10.1111/j.1461-0248.2009.01422.x

Ecology Letters (2010) 13: 246-264 Many of the most interesting questions ecologists ask lead to analyses of spatial data. Yet, perhaps confused by the large number of statistical models and fitting methods available, many ecologists seem to believe this is best left to specialists. Here, we describe the issues that need consideration when analysing spatial data and illustrate these using simulation studies. Our comparative analysis involves using methods including generalized least squares, spatial filters, wavelet revised models, conditional autoregressive models and generalized additive mixed models to estimate regression coefficients from synthetic but realistic data sets, including some which violate standard regression assumptions. We assess the performance of each method using two measures and using statistical error rates for model selection. Methods that performed well included generalized least squares family of models and a Bayesian implementation of the conditional auto-regressive model. Ordinary least squares also performed adequately in the absence of model selection, but had poorly controlled Type I error rates and so did not show the improvements in performance under model selection when using the above methods. Removing large-scale spatial trends in the response led to poor performance. These are empirical results; hence extrapolation of these findings to other situations should be performed cautiously. Nevertheless, our simulation-based approach provides much stronger evidence for comparative analysis than assessments based on single or small numbers of data sets, and should be considered a necessary foundation for statements of this type in future.