ABSTRACT
This chapter introduces the principal elements of hypothesis testing in the context of single sample comparisons. In other words, comparing a single sample of measurements against a specified or hypothesised value. Hypotheses can be one-tailed or two-tailed. The key word that signals whether the hypotheses are one- or two-tailed are less than, greater than (for one-tailed), and equal to (for two-tailed). The chapter illustrates the acceptance/rejection regions for one and two-tailed hypotheses with respect to the normal and t-distributions. Once the question has been formulated, the choice of statistical test is determined by sample size and whether the data conform to a normal distribution. The chapter discusses the methods that one can employ to analyse data that do not conform to a normal distribution. When samples sizes are large, alternative forms of all the non-parametric tests can be used that are based upon the normal distribution.
