Source: Color bar created by Jonathan O, Pain Scale by Joseph G
In this tutorial, you're going to learn about the difference between qualitative data and quantitative data. Qualitative data is also often called categorical data. It stated that is not really numerical in the sense that we can do numerical operations with it, like adding the numbers together or finding an average, but rather it fits in the category.
So an example would be gender, male and female. That's a qualitative variable with two categories. Letter grades, zip codes-- again, which are numbers, but not really in the sense that you can do mathematics with them. You shouldn't do arithmetic-- find an average zip code, for instance. The purpose of zip codes is to divide areas into categories. And then finally, hair color is yet another example.
Qualitative data also, it's important to know, can be divided further into two categories. One is called nominal measurements. And the order of the listed categories doesn't really make a whole lot of different. So for instance, if you were asked your favorite color. It doesn't really matter if I put this in the order of say the color spectrum, red, orange, yellow, green, blue, purple. I don't have to put it in that order. It doesn't really make a difference.
With nominal data, it only makes sense to reference which category has the largest frequency. So you wouldn't say whether the people who say red versus the people who say blue is their favorite color, whether it increases from left to right, because the order doesn't really matter. The only thing that needs referencing is the largest category. So we could say, well, most people said that green was their favorite color.
Whereas with ordinal measurement, the order of the listed categories is in fact important. One example of that would be the pain scale, where you wouldn't want to mix up the orders here, because the one on the furthest left means that it hurts the least and the one on the furthest to the right means that it hurts the worst.
On the other hand, you have quantitative data. Quantitative data is expressed numerically. And it makes sense to do numerical operations with it, like finding averages or adding them together. So for instance, age is a quantitative value as is weight, commute time to work, and the outdoor temperature. So all of these are measured in numbers. And it makes sense to find, for instance, averages of these. So you can do numerical operations with them.
It's important to note that when we discuss displays of data, we will use different displays for qualitative data than we will with quantitative data. And we do different statistical operations depending on the type of data that we have.
So to recap, data that we use in statistics falls under one of two broad classification, either categorical, which is called qualitative or numerical, which is quantitative. Again the numerical values have to make sense to do numerical operations with them. We'll treat them differently when organizing graphical displays and doing all of our statistics with them. So we have qualitative and quantitative. And then within the qualitative realm, there's a nominal, which just means that the names are important, versus ordinal, which means the order is also important. Good luck and we'll see you next time.
Categorical data with qualities that cannot be ordered or ranked.
Categorical data with qualities that can be ordered or ranked.
Data that describes. It can't be measured or used for arithmetic.
Data that is numerical. It can be measured and it can be used for arithmetic. .