"I can see nothing," said I, handing it back to my friend. "On the contrary, Watson, you can see everything. You fail, however, to reason from what you see. You are too timid in drawing your inferences." | ||
| --Sir Arthur Conan Doyle, The Adventure of the Blue Carbuncle | ||
In the previous chapter, we introduced a variety of numerical and visual approaches to understand the normal distribution. We discussed descriptive statistics, such as the mean and standard deviation, and how they can be used to summarize large amounts of data succinctly.
A dataset is usually a sample of some larger population. Sometimes, this population is too large to be measured in its entirety. Sometimes, it is intrinsically unmeasurable, either because it is infinite in size or it otherwise cannot be accessed directly. In either case, we are forced to generalize from the data that we have.
In this chapter, we consider statistical inference: how we can go beyond simply describing the samples of data and...