Premium
A Spatial Analysis of Variance Applied to Soil‐Water Infiltration
Author(s) -
Gotway Carol A.,
Cressie Noel A. C.
Publication year - 1990
Publication title -
water resources research
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.863
H-Index - 217
eISSN - 1944-7973
pISSN - 0043-1397
DOI - 10.1029/wr026i011p02695
Subject(s) - spatial dependence , spatial correlation , infiltration (hvac) , spatial variability , spatial analysis , statistics , soil science , mathematics , variance (accounting) , inference , geostatistics , environmental science , hydrology (agriculture) , geotechnical engineering , geology , computer science , geography , meteorology , accounting , artificial intelligence , business
A spatial analysis of variance uses the spatial dependence among the observations to modify the usual inference procedures associated with a statistical linear model. When spatial correlation is present, the usual tests for presence of treatment effects may no longer be valid, and erroneous conclusions may result from assuming that the usual F ratios are F distributed. This is demonstrated using a spatial analysis of soil‐water infiltration data. Emphasis is placed on modeling the spatial dependence structure with geostatistical techniques, and this spatial dependence structure is then used to test hypotheses about fixed effects using a nested linear model.