Key points are not available for this paper at this time.
It is suggested that the covariance method of statistical analysis is of considerable value in correcting for uncontrolled inequalities arising early in an experiment, and in analysing the effects of developmental factors on yield. As an example its application to the results of an experiment with beans is described. It is with great pleasure that the writers acknowledge their indebtedness to Dr J. Wishart for his helpful criticism throughout the work.
Garner et al. (Sun,) studied this question.