The Influence of Systematic Plot Arrangement upon the Estimate of Error in field Experiments.

Abstract

Summary and Conclusions The effect of systematic plot distribution upon the estimate of error of a field-plot experiment of 5 × 5 plots has been studied on ninety-one blocks taken from eight different uniformity trials, representing a wide variation in plot size and plot shape, crop, climate, and soil. The arrangements studied are: two different knight's moves, two different diagonal arrangements, and eight irregular arrangements, seven of which have been chosen at random. The investigation has shown that the use of systematic plans introduces a bias in the estimate of the error of the experiment. The use of the knight's move arrangement causes an over-estimation of the error, whereas the use of the diagonal causes an under-estimation.