Consecuencias de la estructura espacial de los datos en el diseño y análisis de experimentos en campo

[EN] Many traits assessed in field ecological trials show nonrandom spatial structures that may affect the efficiency of standard statistical analyses. Although several more or less sophisticated experimental designs may improve this efficiency by controlling the spatial variation, there are many si...

Descripción completa

Detalles Bibliográficos
Autor: Zas Arregui, Rafael
Tipo de recurso: artículo
Fecha de publicación:2006
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/45589
Acceso en línea:http://hdl.handle.net/10261/45589
Access Level:acceso abierto
Palabra clave:Autocorrelación espacial
Análisis espacial
Geoestadística
Semivariogramas
Spatial autocorrelation
Spatial analysis
Geostatistics
Semivariograms
Kriging
Descripción
Sumario:[EN] Many traits assessed in field ecological trials show nonrandom spatial structures that may affect the efficiency of standard statistical analyses. Although several more or less sophisticated experimental designs may improve this efficiency by controlling the spatial variation, there are many situations where designs can not be properly arranged to actual spatial patterns. In such cases, spatial analysis techniques become essential to correctly analyse spatial autocorrelated data. In this paper, the effects of spatial autocorrelation on the results of conventional statistical analysis are discussed, and a spatial adjustment procedure, based on geostatistics, is proposed to be used when data are spatially autocorrelated. A case study is presented to show how conventional analysis of spatially autocorrelated data may give completely erroneous conclusions.Many traits assessed in field ecological trials show nonrandom spatial structures that may affect the efficiency of standard statistical analyses. Although several more or less sophisticated experimental designs may improve this efficiency by controlling the spatial variation, there are many situations where designs can not be properly arranged to actual spatial patterns. In such cases, spatial analysis techniques become essential to correctly analyse spatial autocorrelated data. In this paper, the effects of spatial autocorrelation on the results of conventional statistical analysis are discussed, and a spatial adjustment procedure, based on geostatistics, is proposed to be used when data are spatially autocorrelated. A case study is presented to show how conventional analysis of spatially autocorrelated data may give completely erroneous conclusions.