Types of

Variables Prajkta

Bhide, PhD

What is a variable?
➢ A variable is a quantity or a factor in which the value varies as opposed to
a constant.
• Can be measured – blood pressure (mm Hg), body temperature, illness
 episodes, body fat %, births/deaths, sex etc.
• Can be manipulated / controlled - exercise for 5 min or 30 min, drug
dosage 120 mg vs 180 mg, sleep for 8 hours or stay up all night etc. •
Skin colour/presence of disease/genetics

❑ Dependent and Independent Variables

❑ Categorical and Continuous Variables

2
3
Independent variable
Dependent variable
• An independent variable is a
• A dependent variable is one that
variable whose value is not
is influenced by other variables.
affected by other variables.

Independent variable

Influences
 Dependent variable
• Explanatory variable, exposure
variable, input variable,
manipulated variable, predictor
variable

Crocin Fever
Dosage Body temperature
• Outcome variable
4

Independent variable Dependent variable

variables.
• In an experiment, the researchers
manipulate the independent • Not all independent variables can
variables, not the dependent be manipulated e.g. age, sex
 • In an experiment, researchers responds to a change in the
assess how the dependent variable independent variable.

Independent variables Dependent

Skilled birth attendants variables Maternal
mortality

Smoking Lung cancer

Exercise / physical activity Obesity

5
MTHFR genotypes in
NTD in offspring
mother

Dependent variable
Independent variables

7
 How long
you sleep affects your test score.

Your test
score affects how long you sleep.
 8

Types of Variables
• Variables can be classified into one of four types, depending on the type of
scale used to characterize their values:
variable 4. Ratio-scale
variable
1. Nominal-scale Categorical variables
variable 2. Ordinal-scale
variable 3. Interval-scale
 Continuous variables

Categorical variable
• Qualitative
• Arranged into categories

• Examples: vaccination
status, MTHFR genotypes,
pain scale etc.
• Nominal
• Ordinal

10

Nominal-scale

variables ➢ Two or more categories without any

intrinsic order to them

• Sex: male / female

 • Disease (e.g. TB): yes / no Possible to have
• Type of hospital: public / private • moreDichotomous / binary
MTHFR genotypes: CC / CT / TT • Possible to have more
Country of residence: many options

• Any numerical values at the nominal level of measurement should not be treated as a
quantitative variable. An example of this would be a serial number or student ID number. It
makes no sense to do any calculation upon these types of numbers.

11

Ordinal-scale variables
➢ Two or more categories which can be ordered or ranked
(hierarchy)
• Ovarian cancer: Stage I, II, III, or IV

Cancer
remission
yes/no –
nominal,
binary
• However, the levels can be ranked, we cannot place a "value" to
them; we cannot say that ‘II’ is twice as bad as ‘I’.
12

How often do you exercise?

Likert scale
• There is an obvious order or
hierarchy to the categories, but the
difference between Always and
Sometimes is not the same as the
difference between Rarely and
Never.
Always

Sometimes

Rarely

Never
 13

Pain severity
Depression severity

Mild

No

Yes Nominal - binary

 Severe Ordinal
Moderate

14

Continuous variable
• Quantitative
• Associated with numbers

• Examples: height, weight, number of

children, number of hours of sleep
etc.

• Interval
• Ratio
 15

Interval-scale variables
➢ Have a numerical value that can be measured along a continuum
➢ Differences in the numbers represent real differences in the
variable • Temperature measured in degrees Celsius or Fahrenheit -
difference between 20°C and 30°C is the same as 30°C to 40°C
• IQ scores

➢ In an interval scale, a variable can be measured even if it is

negative. Since an integer takes both positive and negative value, the
interval scale also reads negative values.
➢ Arithmetic operations can be performed: only addition and

subtraction 16

Example: days and dates

Date – interval

Day – nominal

17
 Ratio-scale variables
➢ Are interval variables with the added condition that 0 (zero) of the
measurement indicates that there is none of that variable. •
Height
• Weight

• The name "ratio" reflects the fact that the ratio of measurements can be
used. So, for example, a weight 10 kg is twice weight of 5 kg.

Temperature measured in degrees Celsius or Fahrenheit is

not a ratio variable because 0°C does not mean there is no
temperature.
 18

Example: Mantoux tuberculin skin test (TST)

• “positive” or “negative” - nominal

scale

• millimeters of induration - ratio

scale
 19

Discrete variables
➢ Variables that can only take on a finite number of values are called
discrete variables.

➢ Their value is obtained by counting - whole numbers

only • Number of students in class
• Number of prescriptions Ratio-scale variables
• Number of hospital admissions
• Number of children in household

20

Identify
the type
of
variable:
 1. Hypertension: mild, moderate and
severe

2. Pregnancy outcome: stillbirth / live

birth

3. Date of diagnosis of a disease

4. Age in years

21

Derived Variables
• A Derived Variable is a variable defined by a function or expression in
terms of other variables.
• They are variables that you create by calculating or categorizing variables
that already exist in your data set.
• Derived variables are used in the same way as any other variable.

• E.g. BMI (continuous) = derived from height and weight (both continuous).
BMI categories (categorical) would be a separate variable.
• E.g. Income categories (categorical) = by categorizing the actual income
data (continuous)
Age as a variable
• Age differs from the majority of other variables because age does not
follow the usual rules for rounding to the nearest integer. • For most
variables, 15.99 can be rounded to 16.
• However, an adolescent who is 15 years and 360 days old cannot
claim to be 16 years old (and hence get his/her driver’s license or
learner’s permit) for at least 5 more days.
Category Age precision
Adults Years
Children Months
Neonates Days

30-34
0-4
35-39
5-9
40-44
10-14
45-49
15-19
50-54
20-24
55-59
25-29
60-64
 65-69 10 - 14
70-74 15- 19
75-79 20 - 24
80-84 25 - 44
85+ 45 - 64
65 - 79
Age group in Census 0 -4
80+
5 -9

Reading …
• https://www.cdc.gov/csels/dsepd/
ss1978/lesson2/section2.html

• https://www.scribbr.com/method
ology/types-of-variables/
• https://statistics.laerd.com/statisti
cal-guides/types-of-variable.php

25