Free Trial

Safari Books Online is a digital library providing on-demand subscription access to thousands of learning resources.


Share this Page URL
Help

28 The Financial Times Guide to Business Numeracy Analysing data Statistics is the science of analysing data. It tells us how data can be col- lected, organised and analysed, and how to draw conclusions from the data correctly. Without statistics, it would be impossible to perform the calculations behind many familiar things such as: O O O O O O O O O O O O O O political polls; the popularity of a website; monthly unemployment figures; the top 20 music albums; the quality control of consumer products; the audience ratings for TV programmes; the planning of marketing campaigns. Statistics are used intensively in business and there are a large number of statistical tests available. In this section we will look at the concept of sam- pling, review some of the commonly used statistical tests, and then see how to interpret the results through statistical inference. It takes skill and judgement to choose the appropriate test for the circum- stances. Suffice it to say that statisticians are not made overnight, and that the purpose of presenting the tests here is to give you a `feel' for the kinds of manipulations that statisticians can perform on raw data; getting a complete grasp of the subject will require further study, preferably under the guidance of a teacher. You will find that tests often require the use of special tables ­ these are not included in this book, but you will be able to find them in many specialist textbooks. Sampling Suppose you want to conduct a survey of German consumers. Clearly, it would be a huge undertaking to interview every single person in the popu- lation, so you decide to survey a smaller number of people in the hope that you can generalise about the whole population from the results you get; this is called sampling. But what if you only interviewed people living in Stuttgart? Your results probably wouldn't be very representative of everyone living in Germany. Important: to get a representative sample, everyone in the population should have the same chance of being chosen for the sample.