Categorical Data

All right, welcome. Next we’re going to talk about different levels of measurement. Now, these are different ways that we can represent information and data. And I want to talk through two of them. The first I want to talk through is called nominal. This is a type of data you’re really familiar with. It’s just categories. So for instance, we might look at the colour of something or maybe your favourite food. This is a common type of data where we just have people, or items, or objects or whatever grouped into categories. And the only information it contains is the category itself. The next type of data that we see is called ordinal. It’s essentially the same thing.

But this is now your categories have an order to them. This is actually a lot more common than you might think. For example, if we ask somebody a question, how happy are you with your job, and gave them three answers– not at all, somewhat, or very– this is actually an ordinal variable. Why? Because they’ve only responded with one of these three categories. But they do have an order to them. Clearly somewhat is more than not at all. And clearly very is more than somewhat. But we don’t actually have some sort of unit of measure here. I don’t know how big the gap is between those. There’s not some sort of consistent space or measure to them.

So these are going to contain categories with order in an ordinal variable. How is this data represented in the data that you might analyse? Often it’s represented with numbers. For instance, maybe we’ve coded them 1, 2, and 3 in that last example. Or they might be represented in text. Either way, they’re very common variable types that you’re going to come across a lot in the data that you analyse.