Welcome to Really Simple Statistics (RSS). There are lots of places online where you can ponder over the minute details of complicated equations but very few places that make statistics understandable to everyone. I won’t explain exceptions to the rule or special cases here. Let’s just get comfortable with the fundamentals.
Welcome to Really Simple Statistics (RSS). There are lots of places online where you can ponder over the minute details of complicated equations but very few places that make statistics understandable to everyone. I won’t explain exceptions to the rule or special cases here. Let’s just get comfortable with the fundamentals.
One of the first things people learn in statistics class is that there are different kinds of numbers. We’ve gotten so used to treating all numbers the same but many people find the concept difficult to grasp. It’s important to understand the differences because you can’t choose the right statistical test unless you know what kind of data you’re working with. So let’s start with the most basic kind of number: the nominal number.
The word nominal is a hint in itself. Nominal means name so we’re actually starting with a number that really isn’t a number. Nominal numbers are numbers that get assigned to things where the number has no real meaning. You could call a couch Arnold or Triangle or 7 or Blue but it’s still just a couch. 7 might be a number, but it is being used as a name. Here are some examples of nominal data and variables.
- A variable that lists out people’s names. If you think about an Excel spreadsheet listing your friends and family names and addresses, the column that includes their name is nominal. “John” isn’t twice as much as “Mary” and “Harold” isn’t larger than “Earnest.” Each word is simply a name.
- Gender: Even if you assign the number “1″ to women and the number “2″ to men, there is no meaning behind those numbers. Women aren’t twice as human as men. Men aren’t half as alive as women. The numbers are just a convenient way to code or name the two options in a dataset.
- Region: You might have a variable that identifies whether people live in the city or the country. For convenience sake, you might decide to code people who live in the city as “1″ and people who live in the country as “2.” But, we know that cities aren’t half as liveable as the countryside and the countryside isn’t twice as fun as living in the city.
- Other nominal variables: Flavours of cookies (chocolate, oatmeal), types of furniture (couch, chair), types of animals (dog, cat, goat), names of cities (london, paris, greece), shapes (circle, square, triangle), days of the week (friday, wednesday), months of the year (october, april), personality characteristics (shy, creative, intelligent), brand used (ford, toyota)
The rule of thumb is that if you can figure out a legitimate reason for assigning a specific number to something, it is no longer a nominal variable. It’s that simple.
