Introduction to Statistical Inference

Abstract

In Chapter 1 we stated that statistics can be divided into descriptive statistics and inferential statistics. The former is used to arrange, present and summarise the data on some variable so that its principal features can be more readily identified. The three features which we find most useful for summarising data are: a measure of location (for example, the arithmetic mean); a measure of dispersion (typically the standard deviation or variance); and some idea of the shape of the distribution of the data (if the distribution is normal or approximately so, we can use the area properties of the standard normal distribution). In descriptive statistics no serious attempt is made to analyse the data or to generalise the results to larger groups.