In this section, you will learn about the assumptions about data that must be met in order for the Classical Linear Model to produce reliable estimates.
We should be clear from the outset: while these are referred to as assumptions it is not the case that you can simply assume them to be true about the data that you are using.
While we will use the term assumptions throughout the unit, you might do well to think of them as requirements of the data, or conditions that must be true about the data.
OLS regression as an algorithm is a jackhammer: the algorithm, even when run in small samples, will almost always produce some result. The Classical Linear Model is a method of reasoning about whether these results are useful