Experimental Design

Experimental design is not directly related to chemical analysis, but it is important in that it determines the number of samples for processing. This could mean that there are too many tests for the laboratory to fit into its schedule, bearing in mind that there are many other customers clamouring for laboratory services. It could also mean that the cost is prohibitive for the funds available for the project.

Some of the books on the design of scientific experiments appear far too theoretical for use in college field trials. However, three books in particular have proved useful in this Institute:

• Statistical Procedures for Agricultural Research, 2nd edn. Gomez, K.A. and Gomez, A.A. John Wiley & Sons, 1984.

• Agricultural Experimentation. Little, T.M. and Hills, F.J. John Wiley & Sons, 1978.

• Statistical Methods in Agriculture and Biology, 2nd edn. Mead, R., Curnow, R.N. and Hasted, A.M. Chapman and Hall, 1993.

For example, the book by Gomez and Gomez describes many possible designs such as the Latin square and the lattice designs. The former can handle simultaneously two known sources of variation among experimental units. Chapters deal with 'Sampling in experimental plots', and the 'Presentation of research results'.

© 2002 CAB International. Methods in Agricultural Chemical Analysis: a Practical Handbook (N.T. Faithful!)

0 0

Post a comment