Variable vs Observational Unit
Both terms below come up in the same part of the course, and students mix them up. Here is each one defined on its own, side by side, so you can see where they part company.
Variable
Variables and data types
A variable is a characteristic that can change from one observational unit to another, and it is what you record about each individual.
The observational unit is what you measured; the variable is what you recorded about it, and it earns the name variable because its value changes from one unit to the next. Variables come in two types: categorical ones take category names or group labels, and quantitative ones take numerical values for a measured or counted quantity, usually with units. For example, across 30 students, grade level is categorical while commute time in minutes is quantitative, so a mean commute of 14.5 minutes is meaningful and a mean grade level is not. A numerical summary of a variable is a parameter for a population and a statistic for a sample.
Observational unit
Variables and data types
An observational unit is the item or individual from which a datum is collected, that is, one row of the data set.
Naming the observational unit first is the habit that keeps a study straight: the unit is the who or the what, and the variables are what you record about it. For example, in a study of 200 cars the observational unit is one car, while make is a categorical variable recorded on it and fuel economy in miles per gallon is a quantitative one. Get the unit wrong and every count after it is wrong, since 40 schools and 40,000 students are different data sets with different sample sizes. In an experiment, the observational unit a treatment is assigned to is called the experimental unit, or a subject when the units are people.