Bootstrapped ordination: a method for estimating sampling effects in indirect gradient analysis

Indirect gradient analysis, or ordination, is primarily a method of exploratory data analysis. However, to support biological interpretations of resulting axes as vegetation gradients, or later confirmatory analyses and statistical tests, these axes need to be stable or at least robust into minor sampling effects. We develop a computer-intensive bootstrap (resampling) approach to estimate sampling effects on solutions from nonlinear ordination. We apply this approach to simulated data and to three forest data sets from North Carolina, USA and examine the resulting patterns of local and global instability in detrended correspondence analysis (DCA) solutions. We propose a bootstrap coefficient, scaled rank variance (SRV), to estimate remaining instability in species ranks after rotating axes to a common global orientation. In analysis of simulated data, bootstrap SRV was generally consistent with an equivalent estimate from repeated sampling. In an example using field data SRV, bootstrapped DCA showed good recovery of the order of common species along the first two axes, but poor recovery of later axes. We also suggest some criteria to use with the SRV to decide how many axes to retain and attempt to interpret.

[1]  Hugh G. Gauch,et al.  Multivariate analysis in community ecology , 1984 .

[2]  Mark V. Wilson.  A Statistical Test of the Accuracy and Consistency of Ordinations , 1981 .

[3]  Robert Tibshirani,et al.  Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy , 1986 .

[4]  M. Hill.  Correspondence Analysis: A Neglected Multivariate Method , 1974 .

[5]  J. Wilson,et al.  Methods for detecting non-randomness in species co-occurrences: a contribution , 1987, Oecologia.

[6]  M. O. Hill,et al.  DECORANA - A FORTRAN program for detrended correspondence analysis and reciprocal averaging. , 1979 .

[7]  Jacob Weiner,et al.  Size Hierarchies in Experimental Populations of Annual Plants , 1985 .

[8]  Peter R. Minchin,et al.  Simulation of multidimensional community patterns: towards a comprehensive model , 1987, Vegetatio.

[9]  Robert H. Whittaker,et al.  Ordination of Plant Communities , 1978, Handbook of Vegetation Science.

[10]  M. Hill,et al.  Detrended correspondence analysis: an improved ordination technique , 1980 .

[11]  J. Oksanen.  A note on the occasional instability of detrending in correspondence analysis , 1988, Vegetatio.

[12]  Byron K. Williams,et al.  Some Observations of the Use of Discriminant Analysis in Ecology , 1983 .

[13]  H. Gitay,et al.  Does niche limitation exist , 1987 .

[14]  B. Efron.  Better Bootstrap Confidence Intervals , 1987 .

[15]  H. G. Gauch,et al.  Simulation of community patterns , 1976, Vegetatio.

[16]  R. Whittaker,et al.  GRADIENT ANALYSIS OF VEGETATION* , 1967, Biological reviews of the Cambridge Philosophical Society.

[17]  D. H. Knight,et al.  Aims and Methods of Vegetation Ecology , 1974 .

[18]  Hugh G. Gauch,et al.  A COMPARATIVE STUDY OF RECIPROCAL AVERAGING AND OTHER ORDINATION TECHNIQUES , 1977 .

[19]  Relations between community theory and community analysis in vegetation science: some historical perspectives , 1987 .

[20]  M. Austin,et al.  Models for the analysis of species' response to environmental gradients , 2004, Vegetatio.

[21]  R. Peet,et al.  Hardwood forest vegetation of the North Carolina piedmont. , 1980 .

[22]  J. A. Hartigan,et al.  [Bootstrap Methods for Standard Errors, Confidence Intervals, and Other Measures of Statistical Accuracy]: Comment , 1986 .

[23]  R. Knox,et al.  Putting Things in Order: The Advantages of Detrended Correspondence Analysis , 1988, The American Naturalist.

[24]  P. Diaconis,et al.  Computer-Intensive Methods in Statistics , 1983 .

[25]  R. Clarke,et al.  Theory and Applications of Correspondence Analysis , 1985 .

[26]  B. Efron.  The jackknife, the bootstrap, and other resampling plans , 1987 .

[27]  M. Fasham,et al.  A Comparison of Nonmetric Multidimensional Scaling, Principal Components and Reciprocal Averaging for the Ordination of Simulated Coenoclines, and Coenoplanes , 1977 .

[28]  M. Austin,et al.  An Ordination Study of a Chalk Grassland Community , 1968 .

[29]  P. Schönemann,et al.  Fitting one matrix to another under choice of a central dilation and a rigid motion , 1970 .

[30]  Andrew R. Baggaley,et al.  Deciding on the ratio of number of subjects to number of variables in factor analysis , 1982 .

[31]  László Orlóci,et al.  Applying Metric and Nonmetric Multidimensional Scaling to Ecological Studies: Some New Results , 1986 .

[32]  Peter R. Minchin,et al.  An evaluation of the relative robustness of techniques for ecological ordination , 1987 .

[33]  R. Whittaker,et al.  A comparative study of nonmetric ordinations. , 1981 .

[34]  M. Palmer,et al.  Fractal geometry: a tool for describing spatial patterns of plant communities , 1988, Vegetatio.

[35]  Hugh G. Gauch,et al.  Noise Reduction By Eigenvector Ordinations , 1982 .

[36]  Mike P. Austin,et al.  Continuum Concept, Ordination Methods, and Niche Theory , 1985 .

[37]  Jan de Leeuw,et al.  A special Jackknife for Multidimensional Scaling , 1986 .

[38]  Sharon L. Weinberg,et al.  Confidence regions for INDSCAL using the jackknife and bootstrap techniques , 1984 .