ABSTRACT
With an understanding of the framework within which statistical tests operate, we are now in a position to see how some of the more widely used tests can be applied. We will look at:
• The t test for independent samples • The t test for paired samples • The Mann-Whitney U test for independent samples • The Wilcoxon signed-rank test for paired samples • The Chi-square (X2) test for independent samples • Tests of association • Independence and autocorrelation • Statistics and the computer
In the previous chapter we looked at the framework within which statistical tests are applied. In the sections that follow we will move on to look at a number of parametric and non-parametric tests designed to carry out a series of commonly required tasks. The aim is not to provide a description of the working method, which any basic statistics textbook will provide. The priority here in is to explain the underlying logic of the test and illustrate how its results might be interpreted. Consistent use of the same data set allows us to make a preliminary comparison of the relative strengths of the different tests.
