Correlation is a statistical measure used to describe the relationship between two variables.
If two variables are related to one another, this means there is a pattern in how these two variables vary.
Determining the relationship between two variables requires two scores for each individual, one for each variable. Such a pair of scores is generally referred to as a case.
Knowing the relationship between variables is particularly useful because it allows us to make predictions. Specifically, if we know how two variables are related, then we can use the value for one variable to make a prediction about the value for the other variable.
Knowledge of the relationship between variables is what allows a company such as Netflix to determine which shows to recommend you on the basis of your previously watched shows.
There exists a fairly strong relationship between an adult's height and weight:
- Taller than average people also tend to weigh more than average
- Shorter than average people also tend to weigh less than average
Because of this relationship, we can use our knowledge of a person's height to make a prediction about their weight, and vice versa. For example:
- If we know that a person is taller than average, we can reasonably predict that they will also weigh more than average.
- If we know that a person weighs less than average, we can reasonably predict that they will also be shorter than average.