Optimizing the choice of a spatial weighting matrix in eigenvector-based methods. Bauman, D., Drouet, T., Fortin, M., J., & Dray, S. Ecology, 99(10):2159-2166, 2018.
doi  abstract   bibtex   
Abstract Eigenvector-mapping methods such as Moran's eigenvector maps (MEM) are derived from a spatial weighting matrix (SWM) that describes the relations among a set of sampled sites. The specification of the SWM is a crucial step, but the SWM is generally chosen arbitrarily, regardless of the sampling design characteristics. Here, we compare the statistical performances of different types of SWMs (distance-based or graph-based) in contrasted realistic simulation scenarios. Then, we present an optimization method and evaluate its performances compared to the arbitrary choice of the most-widely used distance-based SWM. Results showed that the distance-based SWMs generally had lower power and accuracy than other specifications, and strongly underestimated spatial signals. The optimization method, using a correction procedure for multiple tests, had a correct type I error rate, and had higher power and accuracy than an arbitrary choice of the SWM. Nevertheless, the power decreased when too many SWMs were compared, resulting in a trade-off between the gain of accuracy and the loss of power. We advocate that future studies should optimize the choice of the SWM using a small set of appropriate candidates. R functions to implement the optimization are available in the adespatial package and are detailed in a tutorial.
@article{
 title = {Optimizing the choice of a spatial weighting matrix in eigenvector-based methods},
 type = {article},
 year = {2018},
 keywords = {Moran's eigenvector maps (MEM),community ecology,community simulation,connection scheme,inference of ecological processes from spatial pat,multiscale spatial patterns,optimization,principal coordinates of neighbor matrices (PCNM),spatial autocorrelation,spatial eigenvector mapping (SEVM),spatial weighting matrix,type I error rate inflation},
 pages = {2159-2166},
 volume = {99},
 id = {0e6eeb9b-c61c-3d11-bee6-8ce92dc58db8},
 created = {2018-11-19T09:13:27.174Z},
 file_attached = {true},
 profile_id = {976aa121-3316-304c-8340-7ca54d70abe6},
 last_modified = {2020-08-07T12:49:26.001Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Bauman2018a},
 private_publication = {false},
 abstract = {Abstract Eigenvector-mapping methods such as Moran's eigenvector maps (MEM) are derived from a spatial weighting matrix (SWM) that describes the relations among a set of sampled sites. The specification of the SWM is a crucial step, but the SWM is generally chosen arbitrarily, regardless of the sampling design characteristics. Here, we compare the statistical performances of different types of SWMs (distance-based or graph-based) in contrasted realistic simulation scenarios. Then, we present an optimization method and evaluate its performances compared to the arbitrary choice of the most-widely used distance-based SWM. Results showed that the distance-based SWMs generally had lower power and accuracy than other specifications, and strongly underestimated spatial signals. The optimization method, using a correction procedure for multiple tests, had a correct type I error rate, and had higher power and accuracy than an arbitrary choice of the SWM. Nevertheless, the power decreased when too many SWMs were compared, resulting in a trade-off between the gain of accuracy and the loss of power. We advocate that future studies should optimize the choice of the SWM using a small set of appropriate candidates. R functions to implement the optimization are available in the adespatial package and are detailed in a tutorial.},
 bibtype = {article},
 author = {Bauman, David and Drouet, Thomas and Fortin, Marie Josée and Dray, Stéphane},
 doi = {10.1002/ecy.2469},
 journal = {Ecology},
 number = {10}
}

Downloads: 0