Hi. This tutorial covers qualitative and quantitative data. So let's just start with a data table. Basically, below is the roster of hockey players. Now, we're really looking at the defense men from the 2012 Minnesota Wild team.
So you can see that there are a lot of different data values in here. So if we look at this data value, 30, that represents the age of Kurtis Foster.
If we look at the L here. The L, this is the shot hand, with L meaning left of Clayton Stoner. If we look at this, this is a data value-- Snowflake, Manitoba. that's Justin Falk. That's the birthplace of Justin Falk.
So we can see that a lot of data here is represented in different ways. Some are numbers. Some are words. So let's see if we can make some distinctions about the different types of data.
So there are many data values represented in the table. The name, shot hand, and birthplace are all considered qualitative or categorical data. Whereas the age, height, weight data values are considered quantitative data.
And let's take a look at jersey number in a second also. so, again, if we look at the name, the shot hand, and the birthplace, that's all qualitative data. Age, height, weight, that's all numerical data.
Now, we can also see that the jersey number are also numbers. But we're going to think, is that really quantitative data? So let's take a look at some definitions now. So we'll start with qualitative data, also known as categorical data.
So qualitative data is data that comes from a variable that has two or more descriptive categories. So if we go back to the hockey roster, if we think about shot hand, there are two descriptive categories. They're either a left-handed shooter or a right-handed shooter. So shot hand would be considered a qualitative variable.
Birthplace-- birthplace has many different descriptive categories. But whatever category you pick, that describes where in this case, the person is from. Some other examples would be name, gender, race, religious affiliation, political party affiliation, college major. Again, those all provide variables that have two or more descriptive categories.
Now, if we think about jersey number or zip code, if you think about zip code, zip code describes where someone lives. And I would consider zip code to be a qualitative variable. Because it is not appropriate to do arithmetic on qualitative data. So it wouldn't make any sense to find an average zip code or to add two zip codes.
So these are both can be considered qualitative variables. And they would produce qualitative data.
Now, if we look at quantitative data, quantitative data is data that is in numerical form. And it is appropriate to do arithmetic like find a mean on the data.
So if we think, again, about the hockey example, age, height, weight would all be considered quantitative variables that would produce quantitative data. It makes sense to take the average age of these players or to find the average height or the average weight. Because it is appropriate to do arithmetic on those data values, we can consider that to be quantitative data.
So some other examples would be commute time, weight of ground beef, temperature, number of siblings. Those would all produce measurable quantities of something. So these would all be considered quantitative variables that would produce quantitative data.
So let's just see if we are understanding qualitative versus quantitative. So let's just go through each of these and decide whether they're qualitative or quantitative. So number of glasses of water drink per day-- is it qualitative or quantitative?
This would be a quantitative variable here. Because we're measuring how many glasses of water. So it's not representing quality. It's representing a quantity. So that would be quantitative.
Two-- grade point average-- grade point average is going to be quantitative. So you're going to have a number. That would make sense to take the average grade point average of a group of students. So that's going to be quantitative.
Duration of last shower-- that's also going to be quantitative. It measures how long someone has been in the shower. Occupation-- occupation now is going to be qualitative. An occupation is a quality about someone that can be broken up into different categories. So occupation is qualitative.
Marital status, again, is going to be qualitative. So it could be married, could be single. It could be divorced. Those all represent qualities of someone.
Number of letters in the first name-- that's quantitative. It's how many letters. Type of newspaper read-- that is going to be qualitative. So quality to be broken down into the different types of newspapers. Hair color-- hair color is also qualitative.
So let's now distinguish a couple of things about qualitative. So there's going to be two types of measurement levels for qualitative data. And those two are what we call nominal and ordinal-- so nominal level of measurement and an ordinal level of measurement.
So nominal level of measurement are qualitative data that cannot be ordered or ranked. Almost all of the data that we've looked at that has been qualitative data has been nominal.
The shot hand-- that is going to be nominal. You can't really order that or rank that. So shot hand would be nominal. Birthplace would be nominal.
We looked at occupation. Occupation is nominal. Now, ordinal level of measurement is qualitative data where data can be ordered or ranked. Some examples of variables with an ordinal level of measurement are going to be level of satisfaction, level of pain, movie ratings-- so the number of stars.
So you can rank if you're dealing with level of pain. If you're doing level of pain on a one through 10 scale, if a bunch of people answered nines, bunch of people answered threes, you can tell that those nines are bigger than the three's.
So the people that measured nine have a much more pain than those that measured three. So when you're dealing with ordinal levels of measurement, you can have numbers. But those numbers, even though the ordinal variable has numbers attached to it, it doesn't necessarily mean that it's quantitative. This will be qualitative, ordinal data.
So just to recap, the two distinctions we made were qualitative versus quantitative. This measure's a quality of something where this measures a quantity of something. And then we also looked at nominal versus ordinal data.
Nominal and ordinal are both types of qualitative data. Nominal generally cannot be ordered or ranked. Ordinal does have some meaningful rankings in orderings. So this has been the tutorial on qualitative versus quantitative data. Thanks for watching.