Spatial modelling: a comprehensive framework for principal coordinate analysis of neighbour matrices (PCNM)

Spatial structures of ecological communities may originate either from the dependence of community structure on environmental variables or/and from community-based processes. In order to assess the importance of these two sources, spatial relationships must be explicitly introduced into statistical models. Recently, a new approach called principal coordinates of neighbour matrices (PCNM) has been proposed to create spatial predictors that can be easily incorporated into regression or canonical analysis models, providing a flexible tool especially when contrasted to the family of autoregressive models and trend surface analysis, which are of common use in ecological and geographical analysis. In this paper, we explore the theory of the PCNM approach and demonstrate how it is linked to spatial autocorrelation structure functions. The method basically consists of diagonalizing a spatial weighting matrix, then extracting the eigenvectors that maximize the Moran's index of autocorrelation. These eigenvectors can then be used directly as explanatory variables in regression or canonical models. We propose improvements and extensions of the original method, and illustrate them with examples that will help ecologists choose the variant that will better suit their needs.

[1]  Daniel A. Griffith,et al.  A Spatial Filtering Specification for the Autologistic Model , 2004 .

[2]  D. Griffith.  Eigenfunction properties and approximations of selected incidence matrices employed in spatial analyses , 2000 .

[3]  G. Norcliffe.  On the Use and Limitations of Trend Surface Models , 1969 .

[4]  Pedro R. Peres-Neto,et al.  Patterns in the co-occurrence of fish species in streams: the role of site suitability, morphology and phylogeny versus species interactions , 2004, Oecologia.

[5]  J. Ord,et al.  Spatial and temporal analysis in ecology , 1981 .

[6]  R. Sokal,et al.  Spatial autocorrelation in biology: 1. Methodology , 1978 .

[7]  T. Eo.  Partialling out the spatial component of ecological variation: questions and propositions in the linear modelling framework , 1998 .

[8]  Daniel A. Griffith,et al.  A spatial filtering specification for the auto-Poisson model , 2002 .

[9]  K. Gaston,et al.  Spatial patterns in the species richness of birds in the New World , 1996 .

[10]  Laurence S. Freedman,et al.  The problem of underestimating the residual error variance in forward stepwise regression , 1992 .

[11]  Daniel A. Griffith,et al.  SPATIAL AUTOCORRELATION and EIGENFUNCTIONS OF THE GEOGRAPHIC WEIGHTS MATRIX ACCOMPANYING GEO‐REFERENCED DATA , 1996 .

[12]  Dennis K. J. Lin,et al.  FORWARD SELECTION ERROR CONTROL IN THE ANALYSIS OF SUPERSATURATED DESIGNS , 1998 .

[13]  Helene H. Wagner,et al.  DIRECT MULTI‐SCALE ORDINATION WITH CANONICAL CORRESPONDENCE ANALYSIS , 2004 .

[14]  Bradley P Carlin,et al.  Generalized Hierarchical Multivariate CAR Models for Areal Data , 2005, Biometrics.

[15]  Robert R. Sokal,et al.  Testing Statistical Significance of Geographic Variation Patterns , 1979 .

[16]  T. Simons,et al.  Spatial autocorrelation and autoregressive models in ecology , 2002 .

[17]  Daniel A. Griffith,et al.  A linear regression solution to the spatial autocorrelation problem , 2000, J. Geogr. Syst..

[18]  P. Aubry.  Le traitement des variables régionalisées en écologie : apports de la géomatique et de la géostatistique , 2000 .

[19]  A. Getis,et al.  Comparative Spatial Filtering in Regression Analysis , 2002 .

[20]  Juan Freire,et al.  Information-theoretic approach for selection of spatial and temporal models of community organization , 2003 .

[21]  R. Pace,et al.  Sparse spatial autoregressions , 1997 .

[22]  P. Legendre,et al.  Multiscale spatial distribution of a littoral fish community in relation to environmental variables , 2005 .

[23]  Hanna Tuomisto,et al.  DISSECTING THE SPATIAL STRUCTURE OF ECOLOGICAL DATA AT MULTIPLE SCALES , 2004 .

[24]  Daniel Wartenberg,et al.  Canonical Trend Surface Analysis: A Method for Describing Geographic Patterns , 1985 .

[25]  Roger Bivand,et al.  Spatial econometrics functions in R: Classes and methods , 2002, J. Geogr. Syst..

[26]  Clifford M. Hurvich,et al.  Regression and time series model selection in small samples , 1989 .

[27]  M. Wall.  A close look at the spatial structure implied by the CAR and SAR models , 2004 .

[28]  Pierre Legendre,et al.  All-scale spatial analysis of ecological data by means of principal coordinates of neighbour matrices , 2002 .

[29]  Robert R. Sokal,et al.  Approximate analysis of variance of spatially autocorrelated regional data , 1990 .

[30]  L. Anselin,et al.  Fast maximum likelihood estimation of very large spatial autoregression models: a characteristic polynomial approach , 2001 .

[31]  J. Gower.  Some distance properties of latent root and vector methods used in multivariate analysis , 1966 .

[32]  P. Legendre.  Spatial Autocorrelation: Trouble or New Paradigm? , 1993 .

[33]  Daniel A. Griffith,et al.  A Variance-Stabilizing Coding Scheme for Spatial Link Matrices , 1999 .

[34]  Daniel A. Griffith,et al.  PRACTICAL HANDBOOK of Spatial Statistics , 1998 .

[35]  P. Legendre,et al.  Partialling out the spatial component of ecological variation , 1992 .

[36]  R. Geary,et al.  The Contiguity Ratio and Statistical Mapping , 1954 .

[37]  W..  Relative Neighborhood Graphs and Their Relatives , 2004 .

[38]  D Hémon,et al.  Assessing the significance of the correlation between two spatial processes. , 1989, Biometrics.

[39]  S. Dray,et al.  Broad-scale biodiversity pattern of the endemic tree flora of the Western Ghats (India) using canonical correlation analysis of herbarium records , 2003 .

[40]  P. Clifford,et al.  Modifying the t test for assessing the correlation between two spatial processes , 1993 .

[41]  N. Pettorelli,et al.  Spatial variation in springtime food resources influences the winter body mass of roe deer fawns , 2003 .

[42]  P. Legendre,et al.  ANALYZING BETA DIVERSITY: PARTITIONING THE SPATIAL VARIATION OF COMMUNITY COMPOSITION DATA , 2005 .

[43]  M. Fortin,et al.  Spatial Analysis: A Guide for Ecologists 1st edition , 2005 .

[44]  Daniel A. Griffith,et al.  Semiparametric Filtering of Spatial Autocorrelation: The Eigenvector Approach , 2007 .

[45]  Helene H. Wagner,et al.  SPATIAL COVARIANCE IN PLANT COMMUNITIES: INTEGRATING ORDINATION, GEOSTATISTICS, AND VARIANCE TESTING , 2003 .

[46]  R. Kelley Pace,et al.  Performing large spatial regressions and autoregressions , 1997 .

[47]  T. Boulinier,et al.  Ecological Biogeography of Southern Ocean Islands: The Importance of Considering Spatial Issues , 2001, The American Naturalist.

[48]  Jean Thioulouse,et al.  Multivariate analysis of spatial patterns: a unified approach to local and global structures , 1995, Environmental and Ecological Statistics.

[49]  Hulin Wu,et al.  Modelling the distribution of plant species using the autologistic regression model , 1997, Environmental and Ecological Statistics.

[50]  R. Pélissier,et al.  Within-plot relationships between tree species occurrences and hydrological soil constraints: an example in French Guiana investigated through canonical correlation analysis , 2002, Plant Ecology.

[51]  Fan Chung,et al.  Spectral Graph Theory , 1996 .

[52]  K. Ord.  Estimation Methods for Models of Spatial Interaction , 1975 .

[53]  K. Gaston,et al.  Spatial patterns in the geographic range sizes of bird species in the New World , 1996 .

[54]  H. Preisler,et al.  DEVELOPING PROBABILISTIC MODELS TO PREDICT AMPHIBIAN SITE OCCUPANCY IN A PATCHY LANDSCAPE , 2003 .

[55]  R. Gittins,et al.  Canonical Analysis: A Review with Applications in Ecology , 1985 .

[56]  Stephen H. Roxburgh,et al.  The statistical validation of null models used in spatial association analyses , 1999 .

[57]  Daniel A. Griffith,et al.  On the quality of likelihood-based estimators in spatial autoregressive models when the data dependence structure is misspecified , 1998 .

[58]  A. Getis,et al.  Constructing the Spatial Weights Matrix Using a Local Statistic , 2004 .

[59]  P. Moran.  The Interpretation of Statistical Maps , 1948 .

[60]  Ronald P. Barry,et al.  Monte Carlo estimates of the log determinant of large sparse matrices , 1999 .

[61]  Hjb Birks,et al.  An annotated bibliography of canonical correspondence analysis and related contrained ordination methods 1986-1993. , 1996 .

[62]  R. Gittins,et al.  Trend-Surface Analysis of Ecological Data , 1968 .

[63]  Student,et al.  The Elimination of Spurious Correlation due to Position in Time or Space , 1914 .

[64]  Estimating the residual variance in orthogonal regression , 1991 .

[65]  Pierre Legendre,et al.  Environmental control and spatial structure in ecological communities: an example using oribatid mites (Acari, Oribatei) , 1994, Environmental and Ecological Statistics.

[66]  I. Hanski.  A Practical Model of Metapopulation Dynamics , 1994 .