Spatial Analysis of Field Experiments-An Extension to Two Dimensions

Abstract

The one-dimensional spatial analysis procedure proposed by Gleeson and Cullis (1987, Biometrics 43, 277-288) is extended to two dimensions using the subclass of separable lattice processes to model the errors. Residual maximum likelihood estimation of the models is described and diagnostics for testing model adequacy are derived. Results from the analysis of 24 sets of uniformity data indicate the frequent need for a two-dimensional analysis even when the plot shape is highly rectangular. These results also indicate the potential gain from using a two-dimensional spatial analysis rather than a row + column analysis. An example is presented of the analysis of a field experiment on tobacco.