So what does the course actually cover? We begin in Week 1 by looking at the basic techniques for visualising and summarising data, before moving on to look at what patterns in data can, and can’t, tell us in Week 2.
Often we want to say something about a large population, such as everyone in the UK, but we can’t generally get data on everyone. For this reason we have to take data from just a small sample of the population, say using a survey or an experiment. We look at these kinds methods of collection data in Week 3.
Generally the data we collect is subject to variability – if we were to do a survey with a different collection of people, for example, we would get different data. For this reason, we need to understand sampling variability or uncertainty. So in Week 4 we formalise the concept of uncertainty by introducing probability.
The final two weeks of the course really get to the heart of statistics. Week 5 looks at how we can use sampled data to determine properties of the whole population, for example how we can estimate the number of children in the UK living in poverty. Finally, Week 6 introduces statistical testing, the main way we answer a statistical question such as whether a new drug is worth producing, or whether or not truancy is a bigger problem in larger schools.