PROBABILITY DISTRIBUTIONS OF

DISCRETE RANDOM VARIABLES

Discrete Random Variables

Also called:
Probability distribution
function (PDF)
A variable whose
outcomes depend on a
random experiment Probability Mass
Function (PMF)
A table/function that lists
all the possible outcomes
Finite/countable and the associated
number of outcomes probabilities.
 Notation
Capital letters
are used to
represent Let
𝑃 𝑋=𝑥 X = height
RANDOM
x = 162 cm
VARIABLES (R.V) =𝑃 𝑥
=𝑝 𝑥 𝑃 𝑋 = 162
Lower case =𝑓 𝑥
letters give the
specific values
that the R.V can All these mean the “ The probability that the
height is 162 ”
same thing
take on.
 Example

Let X = the amount of money a student earns per hour (in Rands)

Note:
The random 𝒙 100 120 150 170 Sum
variable (𝑥) can only
take on one value at P(𝒙) 0.15 0.25 0.45 0.15 1
a time

෍𝑃 𝑥 = 1
𝑥
Important
properties of a
discrete random
0 ≤ 𝑃(𝑥) ≤ 1 variable and its
probability
distribution.
 𝒙 100 120 150 170 Sum
P(𝒙) 0.15 0.25 0.45 0.15 1

a) P(earning R100 or R150) = P(earn R100) + P(earn R150)

= 0,15 + 0,45
= 0,6

b) P(earning less than R150) = P(100) + P(120)

= 0,15 + 0,25
= 0,4

c) P(earning at least R120) = P(120) + P(150) + P(170)

= 0,25 + 0,45 + 0,15
= 0,85
Example

Find the value of k such that the following is a valid PDF.

𝒚 -4 0 0.3 2 8
P(𝒚) k 0.125 0.125 0.375 0.125

Remember: The sum of the probabilities must be 1

∴ k + 0.125 + 0.125 + 0.375 + 0.125 = 1

∴ k = 0.25
Cumulative Distribution Function
(C.D.F.)

The probability that X takes on all 𝐹 𝑋 = 𝑃 𝑋 ≤ 𝑥 = ෍ 𝑃(𝑟)

the values less than or equal to x.
𝑟≤𝑥
Example

𝒙 100 120 150 170

P(𝒙) 0.15 0.25 0.45 0.15
F(𝒙) 0.15 0.40 0.85 1
𝐹 120 = 𝑃 𝑋 ≤ 120
= 𝑃 𝑋 = 100) + 𝑃(𝑋 = 120
Example

Find the value of 𝑘 (a constant) below that makes the following a valid probability mass function
(P.M.F): 𝑥2
𝑃 𝑋=𝑥 = for 𝑥 = 1, 2, 3, 4 , 5
𝑘
Solution

To find 𝑘, we will use the following property of a P.M.F: ෍ 𝑃 𝑋 = 𝑥 = 1

i.e: 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + ⋯ + 𝑃 𝑋 = 5 = 1

1 2 22 52
∴ + + ⋯+ =1
𝑘 𝑘 𝑘

55
=1 ∴ 𝑘 = 55
𝑘
 Example continued

𝑥2
𝑃 𝑋=𝑥 = for 𝑥 = 1, 2, 3, 4 , 5
55
We can now use this P.M.F to find probabilities for X:

Solution

a) Find the probability that X is at least 3.

(≥)
𝑃 𝑋 ≥ 3 = 𝑃 𝑋 = 3 + 𝑃 𝑋 = 4 + 𝑃(𝑋 = 5)

32 4 2 52 Sum the
= + +
55 55 55 probabilities over the
range of X.
= 0.9091
b) Find the probability that X is less than 4.
(<)
Solution 𝑃 𝑋 < 4 = 𝑃(𝑋 ≤ 3)
= 𝑃 𝑋 = 1 + 𝑃 𝑋 = 2 + 𝑃(𝑋 = 3)
12 22 32
= + +
55 55 55
= 0.2545

c) Find the probability that X at most 2.

(≤)
Solution 𝑃 𝑋 ≤2 =𝑃 𝑋 =1 +𝑃 𝑋 =2
12 22
= +
55 55
= 0.0910
MEAN, VARIANCE AND STANDARD DEVIATION
OF A DISCRETE RANDOM VARIABLE
The mean or expected value of a random variable X is the average value that we
would expect for X when performing the experiment many times.

The mean/ expected value is calculated using the following formula:

𝐸 𝑋 = 𝜇 = ෍ 𝑥 𝑃(𝑋 = 𝑥) (ON FORMULA SHEET)

𝑥

The variance of a random variable X gives a measure of variation for the different
values of the random variable.
The variance is calculated using the following formula:

𝜎2 = ෍ 𝑥 − 𝜇 2 𝑃(𝑋 = 𝑥) 𝑃 𝑋 = 𝑥 = 𝑝(𝑥)
(ON FORMULA SHEET)
= ෍ 𝑥 2 𝑝 𝑥 − 𝜇2 Easier formula to use
 The standard deviation can be found by square rooting the variance:

𝜎= 𝜎2
Example

Let X = the amount of money a student earns per hour (in Rands). Find the expected amount a
student earns per hour.

𝒙 100 120 150 170 Total

P(𝒙) 0.15 0.25 0.45 0.15 1
𝒙 ×P(𝒙) 15 30 67.5 22.5 135

𝐸 𝑋 = 𝜇 = ෍ 𝑥 𝑃(𝑋 = 𝑥)

= (100 × 0.15) + (120 × 0.25) + (150 × 0.45) + (170 × 0.15)

= 135
 Example continued

Find the standard deviation of the amount a student earns per hour.

𝒙 100 120 150 170 Total

𝜇 = 135 P(𝒙) 0.15 0.25 0.45 0.15 1
𝒙𝟐 P(𝒙) 1500 3600 10125 4335 19560
Solution First find the variance:
𝜎 2 = ෍ 𝑥 2 𝑃 𝑋 = 𝑥 − 𝜇2

= 1002 × 0.15 + 1202 × 0.25 + 1502 × 0.45 + 1702 × 0.15 − 1352

= 19560 − 1352
= 1335 ∴ 𝜎 = 1335 = 36.54
Example
Suppose a game is played with a balanced die where you win R6 when a 3 or 4 is rolled, otherwise you lose R3.
Is this a fair game?

Definition: A fair game is one where the expected gain or loss is zero, i.e. E(X) = 0
Let X = amount you win. Therefore, X can equal 6 or –3 (negative to indicate you lose R3).

Since X = 6 when a 3 or 4 is rolled, P(X = 6) = P(3 or 4 is rolled) =

2
6
Similarly, P(X = –3) = P(1, 2, 5 or 6 is rolled) = . Therefore, the probability distribution of X is as follows:
4
6

𝑥 6 –3 Total
P(𝑥) 2ൗ 4ൗ 6Τ =1
6 6 6

𝒙 ×P(𝒙) 2 -2 0
Since the expected winnings
∴ 𝐸 𝑋 = ෍ 𝑥𝑃(𝑥) = (6)(2ൗ6) + (−3)(4ൗ6) = 0 is zero, this is a fair game.