ABSTRACT
Statistical inference is so important that it will dominate the later chapters of this book. In this chapter we will confine our attention to several widely used population descriptions, which are known as probability distributions. These probability distributions are necessarily more abstract than the frequency distributions of the previous chapter and you may feel that you are being led astray if your main interest is data analysis. Let it be stated very clearly at the outset, therefore, why it is necessary to study probability distributions as a means of describing populations. There are two main reasons: (a) We can use a.probability distribution to predict unusual events. (When
doing so we will be using the probability distribution as a model. Clearly it is important to choose a good model.)
(b) The methods of statistical inference that are described in later chapters
28 Describing the population Table 3.1 Frequency distribution for 50 batches of pigment Number of overloads 0 1 2 3 4 5
Total Number of batches 15 13 11 6 3 2 50
are based on probability distributions. It is necessary to have some appreciation of the assumptions underlying these methods and this is only possible if you have some knowledge of the well-known distributions.
