We have used the t-test in chapter 4 to compare the means of two samples, but we often need to compare the mean values of larger numbers of samples. For example is there a significant difference between the mean diameter of four samples of a species of Jurassic pollen, is the porosity of five sandstones different? Such questions are often asked in all parts of the earth sciences and indeed in many other sciences as well. A comprehensive and powerful set of procedures, all based on the F-test devised by Fisher, originally for agricultural use, and referred to generally as ‘analysis of variance’ have been developed.
Unable to display preview. Download preview PDF.