Premium
An Investigation of Some of the Relationships between Copper, Iron, and Molybdenum in the Growth and Nutrition of Lettuce: I. Experimental Design and Statistical Methods for Characterizing the Response Surface
Author(s) -
Hader R. J.,
Harward M. E.,
Mason D. D.,
Moore D. P.
Publication year - 1957
Publication title -
soil science society of america journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.836
H-Index - 168
eISSN - 1435-0661
pISSN - 0361-5995
DOI - 10.2136/sssaj1957.03615995002100010013x
Subject(s) - design of experiments , factorial experiment , factorial , response surface methodology , greenhouse , nutrient , polynomial , experimental data , mathematics , fertilizer , orthogonal array , computer science , statistics , biological system , environmental science , agronomy , taguchi methods , ecology , biology , mathematical analysis
In studies involving the experimental determination of critical levels of plant nutrients and optimum rates of fertilizer application, the need for the consideration of joint effects of other nutrients has long been realized. Where such joint effects or interactions exist, characterization of the response surface is essential for the realistic evaluation of the responses. The use of the complete factorial experiment provides a means of estimating the response surface; but the number of treatment combinations required, especially where more than two nutrients or factors are involved, has often prohibited their use in field and greenhouse research. Where a polynomial model may be used to approximate a response surface, new experimental designs, known as the composite and rotatable designs, have been developed by Box and Hunter. In these designs, the treatment combinations are selected to allow estimation of the parameters of the model. These designs use considerably fewer treatment combinations for the experiment than required by the complete factorial arrangement. Other important advantages of those designs are discussed. The basis of construction of these designs is briefly discussed and some examples are presented. The details of statistical analysis are illustrated by the use of experimental data from a greenhouse experiment with lettuce.