Variables

A variable is a value or characteristic that can be different from individual

to individual.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

1/5

Variables

A variable is a value or characteristic that can be different from individual

to individual.
Examples:
favorite color
age
population (the individuals might be countries or cities, for example)

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

1/5

Quantitative variables

Quantitative variables have numerical values, often with units of

measurement.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

2/5

Quantitative variables

Quantitative variables have numerical values, often with units of

measurement.
They arise as answers to questions like, How much? or, How many?

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

2/5

Quantitative variables

Quantitative variables have numerical values, often with units of

measurement.
They arise as answers to questions like, How much? or, How many?
Examples:
age (possible units: years)
annual income (possible units: thousands of dollars)
number of children (this is a count and has no other units)

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

2/5

Continuous and discrete quantitative variables

Sometimes we are willing to believe that the values of a quantitative
variable can be arbitrarily close to each other. Such a variable is called
continuous.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

3/5

Continuous and discrete quantitative variables

Sometimes we are willing to believe that the values of a quantitative
variable can be arbitrarily close to each other. Such a variable is called
continuous.
Height, weight, and age are examples of variables often considered
continuous, though in practice we can only measure them up to a certain
degree of accuracy.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

3/5

Continuous and discrete quantitative variables

Sometimes we are willing to believe that the values of a quantitative
variable can be arbitrarily close to each other. Such a variable is called
continuous.
Height, weight, and age are examples of variables often considered
continuous, though in practice we can only measure them up to a certain
degree of accuracy.
But quantitative variables like number of children take on values that are
separated from each other by fixed amounts. For example, the number of
children in a household can be 0, 1, 2, and so on, consecutive values being
separated by 1. But it cant be 1.25. Such variables are called discrete.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

3/5

Continuous and discrete quantitative variables

Sometimes we are willing to believe that the values of a quantitative
variable can be arbitrarily close to each other. Such a variable is called
continuous.
Height, weight, and age are examples of variables often considered
continuous, though in practice we can only measure them up to a certain
degree of accuracy.
But quantitative variables like number of children take on values that are
separated from each other by fixed amounts. For example, the number of
children in a household can be 0, 1, 2, and so on, consecutive values being
separated by 1. But it cant be 1.25. Such variables are called discrete.
The distinction between continuous and discrete isnt absolute.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

3/5

Continuous and discrete quantitative variables

Sometimes we are willing to believe that the values of a quantitative
variable can be arbitrarily close to each other. Such a variable is called
continuous.
Height, weight, and age are examples of variables often considered
continuous, though in practice we can only measure them up to a certain
degree of accuracy.
But quantitative variables like number of children take on values that are
separated from each other by fixed amounts. For example, the number of
children in a household can be 0, 1, 2, and so on, consecutive values being
separated by 1. But it cant be 1.25. Such variables are called discrete.
The distinction between continuous and discrete isnt absolute.
Sometimes we will discretize a continuous variable, for example by
measuring age in completed years.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

3/5

Continuous and discrete quantitative variables

Sometimes we are willing to believe that the values of a quantitative
variable can be arbitrarily close to each other. Such a variable is called
continuous.
Height, weight, and age are examples of variables often considered
continuous, though in practice we can only measure them up to a certain
degree of accuracy.
But quantitative variables like number of children take on values that are
separated from each other by fixed amounts. For example, the number of
children in a household can be 0, 1, 2, and so on, consecutive values being
separated by 1. But it cant be 1.25. Such variables are called discrete.
The distinction between continuous and discrete isnt absolute.
Sometimes we will discretize a continuous variable, for example by
measuring age in completed years.
And sometimes, especially when were doing approximations, we will
consider discrete variables like test scores to be continuous.
Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

3/5

Categorical and qualitative variables

Some variables dont have numerical values; rather, the data fall into
categories that have no particular order or ranking in relation to each
other. Such variables are called categorical or qualitiative.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

4/5

Categorical and qualitative variables

Some variables dont have numerical values; rather, the data fall into
categories that have no particular order or ranking in relation to each
other. Such variables are called categorical or qualitiative.
Examples:
favorite color
gender
nationality

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

4/5

Categorical and qualitative variables

Some variables dont have numerical values; rather, the data fall into
categories that have no particular order or ranking in relation to each
other. Such variables are called categorical or qualitiative.
Examples:
favorite color
gender
nationality
Some variables arent numerical but their values have a natural order or
ranking; such variables are sometimes called qualitative ordinal.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

4/5

Categorical and qualitative variables

Some variables dont have numerical values; rather, the data fall into
categories that have no particular order or ranking in relation to each
other. Such variables are called categorical or qualitiative.
Examples:
favorite color
gender
nationality
Some variables arent numerical but their values have a natural order or
ranking; such variables are sometimes called qualitative ordinal.
Examples:
temperature: low/medium/high
job performance: poor/satisfactory/excellent

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

4/5

Categorical and qualitative variables

Some variables dont have numerical values; rather, the data fall into
categories that have no particular order or ranking in relation to each
other. Such variables are called categorical or qualitiative.
Examples:
favorite color
gender
nationality
Some variables arent numerical but their values have a natural order or
ranking; such variables are sometimes called qualitative ordinal.
Examples:
temperature: low/medium/high
job performance: poor/satisfactory/excellent
Again, these distinctions arent absolute, and we wont spend a lot of time
worrying about them.
Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

4/5

A word of caution
Just because a variable has numerical values, that doesnt mean it is
quantitative.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

5/5

A word of caution
Just because a variable has numerical values, that doesnt mean it is
quantitative.
For example, if your variable is favorite color, you can assign a numerical
code to each color and say that red is 1, blue is 2, and so on. That
doesnt change the variable from categorical to quantitative.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

5/5

A word of caution
Just because a variable has numerical values, that doesnt mean it is
quantitative.
For example, if your variable is favorite color, you can assign a numerical
code to each color and say that red is 1, blue is 2, and so on. That
doesnt change the variable from categorical to quantitative.
You cant do any arithmetic on those numbers. For example, it doesnt
make sense to take their average. The assigned numerical values are just
labels, as were the original words red, blue, and so on.

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

5/5

A word of caution
Just because a variable has numerical values, that doesnt mean it is
quantitative.
For example, if your variable is favorite color, you can assign a numerical
code to each color and say that red is 1, blue is 2, and so on. That
doesnt change the variable from categorical to quantitative.
You cant do any arithmetic on those numbers. For example, it doesnt
make sense to take their average. The assigned numerical values are just
labels, as were the original words red, blue, and so on.
But if you code yes/no answers as 1/0, then the average of all your 1s
and 0s does indeed make sense and turns out to be a very interesting
quantity. Well see this later in the course; stay tuned!

Ani Adhikari and Philip Stark

Statistics 2.1X

Lecture 1.2

5/5