Nearest Neighbour Models in the Analysis of Field Experiments

SUMMARY The method of adjusting plot values by covariance on neighbouring plots in randomized field experiments, suggested by Papadakis in 1937, is re-examined theoretically for both one-dimensional and two-dimensional layouts, making use of Markovian and autonormal models. The gain in efficiency over orthodox randomized block analysis can be appreciable when the number of treatments is fairly large, and can be increased by iterating the analysis; this also reduces the discrepancy between the apparent accuracy from the residual sum of squares, and the true accuracy of the treatment comparisons after adjustment. Some illustrative examples are included.

[1]  R. M. Williams.  EXPERIMENTAL DESIGNS FOR SERIALLY CORRELATED OBSERVATIONS , 1952 .

[2]  O. J. Olesen,et al.  A polycross pattern formula , 1973, Euphytica.

[3]  Restricted randomization for blocks of sixteen plots , 1964, The Journal of Agricultural Science.

[4]  S. Pearce.  An examination of Fairfield Smith's law of environmental variation , 1976, The Journal of Agricultural Science.

[5]  W. T. Federer,et al.  The Use of Covariance to Control Gradients in Experiments , 1954 .

[6]  Description de L'Hétérogénéité des champs d'Experience , 1969 .

[7]  J. Besag.  Statistical Analysis of Non-Lattice Data , 1975 .

[8]  Bernard Prum,et al.  The precision of different experimental designs for a random field , 1977 .

[9]  M. S. Bartlett,et al.  Physical nearest-neighbour models and non-linear time-series. II Further discussion of approximate solutions and exact equations , 1971, Journal of Applied Probability.

[10]  Anthony C. Atkinson,et al.  The use of residuals as a concomitant variable , 1969 .

[11]  Justus Seely,et al.  Quadratic Subspaces and Completeness , 1971 .

[12]  F. Yates.  A new method of arranging variety trials involving a large number of varieties , 1936, The Journal of Agricultural Science.

[13]  M. S. Bartlett,et al.  The approximate recovery of information from replicated field experiments with large blocks , 1938, The Journal of Agricultural Science.

[14]  Richard Bellman,et al.  Introduction to Matrix Analysis , 1972 .

[15]  K. Ord.  Estimation Methods for Models of Spatial Interaction , 1975 .

[16]  D. Lindley,et al.  Bayes Estimates for the Linear Model , 1972 .

[17]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[18]  C. S. Moore,et al.  Reduction of Experimental Error in Perennial Crops,Using Adjustment by Neighbouring Plots , 1976, Experimental Agriculture.

[19]  I. I. Berenblut,et al.  Experimental design in the presence of autocorrelated errors , 1974 .

[20]  H. F. Smith.  An empirical law describing heterogeneity in the yields of agricultural crops , 1938, The Journal of Agricultural Science.

[21]  Batch acceptance schemes based on an autoregressive prior , 1976 .

[22]  M. Healy,et al.  Restricted randomization and quasi-Latin squares , 1950 .

[23]  J. A. Neldee.  New Kinds of Systematic Designs for Spacing Experiments , 1962 .