Abstract
AbstractRegression models for spatially varying data use spatial random effects to reflect spatial correlation structure. Such random effects, however, may interfere with the covariate effect estimates and make them unreliable. This problem, known as spatial confounding, is complex and has only been studied for models with linear covariate effects. However, as illustrated by a forestry example in which we assess the effect of soil, climate, and topography variables on tree health, the covariate effects of interest are in practice often unknown and nonlinear. We consider, for the first time, spatial confounding in spatial models with nonlinear effects implemented in the generalised additive models (GAMs) framework. We show that spatial+, a recently developed method for alleviating confounding in the linear case, can be adapted to this setting. In practice, spatial+ can then be used both as a diagnostic tool for investigating whether covariate effect estimates are affected by spatial confounding and for correcting the estimates for the resulting bias when it is present. Supplementary materials accompanying this paper appear online.
Funder
Engineering and Physical Sciences Research Council
Publisher
Springer Science and Business Media LLC
Subject
Applied Mathematics,Statistics, Probability and Uncertainty,General Agricultural and Biological Sciences,Agricultural and Biological Sciences (miscellaneous),General Environmental Science,Statistics and Probability
Reference32 articles.
1. Augustin N, A. Albrecht K, Anaya-Izquierdo Davis A, Meining S, Puhlmann H, Wood S (2022) Modelling tree survival for investigating climate change effects. arXiv preprint arXiv:2210:02247
2. Clayton DG, Bernardinelli L, Montomoli C (1993) Spatial correlation in ecological analysis. Int J Epidemiol 22(6):1193–1202
3. Damman I, Herrman T, Körver F, Schröck H, Ziegler C (2001) Dauerbeobachtungsflächen Waldschäden im Level II-Programm - Methoden und Ergebnisse der Kronenansprache seit 1983. Bund-Länder-Arbeitsgruppe Level II / Arbeitskreis Krone. BMVEL, Bonn
4. de Vries W, Vel E, Reinds G, Deelstra H, Klap J, Leeters E, Hendriks C, Kerkvoorden M, Landmann G, Herkendell J, Haussmann T, Erisman J (2003) Intensive monitoring of forest ecosystems in Europe: 1. Objectives, set-up and evaluation strategy 174(1)
5. Dietrich H, Wolf T, Kawohl T, Wehberg J, Kändler G, Mette T, Röder A, Böhner J (2019) Temporal and spatial high-resolution climate data from 1961 to 2100 for the german national forest inventory (nfi). Ann For Sci 76(1):1–14