Continuous Discrete Categorical Dichotomous Ordingal Interval Ratio Level
If you're studying for a statistics exam and need to review your data types this article will give you a brief overview with some simple examples.
Because let's face it: not many people study data types for fun or in their real everyday lives.
So let's dive in.
Quantitative vs Qualitative data - what's the difference?
In short: quantitative means you can count it and it's numerical (think quantity - something you can count). Qualitative means you can't, and it's not numerical (think quality - categorical data instead).
Boom! Simple, right?
There's one more distinction we should get straight before moving on to the actual data types, and it has to do with quantitative (numbers) data: discrete vs. continuous data.
Discrete data involves whole numbers (integers - like 1, 356, or 9) that can't be divided based on the nature of what they are.
Like the number of people in a class, the number of fingers on your hands, or the number of children someone has. You can't have 1.9 children in a family (despite what the census might say).
Continuous data, on the other hand, is the opposite. It can be divided up as much as you want, and measured to many decimal places.
Like the weight of a car (can be calculated to many decimal places), temperature (32.543 degrees, and so on), or the speed of an airplane.
Now for the fun stuff.
Qualitative data types
Nominal data
Nominal data are used to label variables without any quantitative value. Common examples include male/female (albeit somewhat outdated), hair color, nationalities, names of people, and so on.
In plain English: basically, they're labels (and nominal comes from "name" to help you remember). You have brown hair (or brown eyes). You are American. Your name is Jane.
Examples:
What color hair do you have?
- Brown
- Blonde
- Black
- Rainbow unicorn
What's your nationality?
- American
- German
- Kenyan
- Japanese
Notice that these variables don't overlap. For the purposes of statistics, anyway, you can't have both brown and rainbow unicorn-colored hair. And they're only really related by the main category of which they're a part.
Ordinal data
The key with ordinal data is to remember that ordinal sounds like order - and it's the order of the variables which matters. Not so much the differences between those values.
Ordinal scales are often used for measures of satisfaction, happiness, and so on. Have you ever taken one of those surveys, like this?
"How likely are you to recommend our services to your friends?"
- Very likely
- Likely
- Neutral
- Unlikely
- Very unlikely
See, we don't really know what the difference is between very unlikely and unlikely - or if it's the same amount of likeliness (or, unlikeliness) as between likely and very likely. But that's ok. We just know that likely is more than neutral and unlikely is more than very unlikely. It's all in the order.
Quantitative data types
Interval Data
Interval data is fun (and useful) because it's concerned with both the order and difference between your variables. This allows you to measure standard deviation and central tendency.
Everyone's favorite example of interval data is temperatures in degrees celsius. 20 degrees C is warmer than 10, and the difference between 20 degrees and 10 degrees is 10 degrees. The difference between 10 and 0 is also 10 degrees.
If you need help remembering what interval scales are, just think about the meaning of interval: the space between. So not only do you care about the order of variables, but also about the values in between them.
There is a little problem with intervals, however: there's no "true zero." A true zero has no value - there is none of that thing - but 0 degrees C definitely has a value: it's quite chilly. You can also have negative numbers.
If you don't have a true zero, you can't calculate ratios. This means addition and subtraction work, but division and multiplication don't.
Ratio data
Thank goodness there's ratio data. It solves all our problems.
Ratio data tells us about the order of variables, the differences between them, and they have that absolute zero. Which allows all sorts of calculations and inferences to be performed and drawn.
Ratio data is very similar interval data, except zero means none. For ratio data, it is not possible to have negative values.
For instance, height is ratio data. It is not possible to have negative height. If an object's height is zero, then there is no object. This is different than something like temperature. Both 0 degrees and -5 degrees are completely valid and meaningful temperatures.
Now that you have a basic handle on these data types you should be a bit more ready to tackle that stats exam.
Learn to code for free. freeCodeCamp's open source curriculum has helped more than 40,000 people get jobs as developers. Get started
Source: https://www.freecodecamp.org/news/types-of-data-in-statistics-nominal-ordinal-interval-and-ratio-data-types-explained-with-examples/
0 Response to "Continuous Discrete Categorical Dichotomous Ordingal Interval Ratio Level"
Post a Comment