11/02/2025
Random Variables and
Probability Distribution
Random Variable
A rule or function that associates exactly one real
number to every outcome in the sample space. It is
usually denoted by a capital letter, say X.
NOTE: All the possible values of the random variable
define mutually exclusive and exhaustive events.
Random Variables and
Probability Distribution
Random Variable
Example: Consider the Ω of the distribution of gears in a four-
gear machine where each gear will be checked if they are
good or bad gears
Ω = { GGGG, GGGB, GGBG, GBGG, BGGG, GGBB, GBGB,
GBBG, BGBG, BBGG, BGGB, GBBB, BGBB, BBGB, BBBG, BBBB}
Let random variable X be the number of bad gears.
Then, for {GGGG}, X = 0
Question: What are the possible values of X?
Answer: X = { 0, 1, 2, 3, 4 }.
1
11/02/2025
Random Variables and
Probability Distribution
Probability Distribution
The set of all possible values of a random variable
together with their corresponding probabilities.
May be presented in three forms:
Tabular
Graphical
Functional
Probability Distribution
Example: Consider the random variable X of the number
of bad gears in a four-gear machine.
𝑃 𝑋=0 =
𝑃 𝑋=1 = and so on…
Tabular Form
4
𝑃(𝑋 = 𝑥) =
𝑥
(0.5) ; 𝑥 = 0,1,2,3,4 Functional Form
2
11/02/2025
Mean of a Random Variable
Denoted by E[X] or 𝜇
Interpreted as the long-run average of the random
variable
Computed as ∑ [𝑥 𝑃(𝑋 = 𝑥)]
Example:
1 4 6 4 1
𝐸[𝑋] = 0 • + 1• + 2• + 3• + 4• =2
16 16 16 16 16
Variance of a Random Variable
Denoted by V[X] or 𝜎
Measures the average deviation of the values of the
random variable from its mean
Computed as ( 𝑥 • 𝑃[𝑋 = 𝑥]) − 𝜇
Example:
1 4 6 4 1
𝑉[𝑋] = 0 • + 1 • + 2 • + 3 • + 4 • −2 =1
16 16 16 16 16
3
11/02/2025
Some Special Discrete Probability Distribution
Bernoulli Distribution
Bernoulli trial is a random experiment where are only two
possible outcomes, “success” or “failure”. The Bernoulli random
variable, X, assumes the value 1 if the trial is a success and 0
otherwise.
Ex. tossing a coin (H or T); result of an exam (P or F);
classifying a number (odd or even)
Functional Form 𝑃(𝑋 = 𝑥) = 𝑝 (1 − 𝑝) ; 𝑥 = 0,1
Mean p
Variance p(1-p)
Some Special Discrete Probability Distribution
Bernoulli Distribution
Example: Based on the past records of PRC, the passing
rate of a civil engineering examinee is 39%, on average.
What is the probability that a randomly selected
examinee will pass this year?:
𝑃(𝑋 = 𝑥) = 𝑝 (1 − 𝑝) ; 𝑥 = 0,1
𝑃 𝑋 = 1 = 0.39 (1 − 0.39) = 0.39
4
11/02/2025
Some Special Discrete Probability Distribution
Binomial Distribution
Binomial experiment consists of n identical and
independent Bernoulli trials. The binomial random
variable, say X, is the number of successes in n Bernoulli
trials.
𝑛
𝑃(𝑋 = 𝑥) = 𝑝 (1 − 𝑝) ; 𝑥 = 0,1,2, . . . , 𝑛
Functional Form 𝑥
Mean np
Variance np(1-p)
Some Special Discrete Probability Distribution
Binomial Distribution
Example: It is known that 40% of cities inoculated with a microbe are
not protected from a certain disease. Let X be the number of
infected cities. If 5 cities are inoculated, find the probability that:
1. no cities was infected by the disease?
5
𝑃(𝑋 = 0) = 0. 4 (0.6) = 0.0778
0
2. more than 3 are infected?
𝑃(𝑋 > 3) = 𝑃(𝑋 = 4) + 𝑃(𝑋 = 5) = 0.0870
E[X] = 5x0.4 = 2 V[X] = 5x0.4x0.6 =1.2
5
11/02/2025
Some Special Discrete Probability Distribution
Binomial Distribution
Example: Suppose a factory produces gears, and each gear has a
90% chance of being good and a 10% chance of being defective. A
quality control inspector checks 4 gears, and we define 𝑋 as the
number of good gears found, find the probability that:
1. no good gears was found?
4
𝑃(𝑋 = 0) = 0. 9 (0.1) = 0.0001
0
2. more than 2 are defective?1
𝑃(𝑋 > 2) = 𝑃(𝑋 = 3) + 𝑃(𝑋 = 4) = 0.9477
E[X] = 5x0.4 = 2 V[X] = 5x0.4x0.6 =1.2
It was found that approximately 30% of all construction
failures are caused by operator error and improper
monitoring. What is the probability that out of the next 20
construction failures, no more than 4 out of 20 such
failures are due to operator error?
Answer: 0.2375
6
11/02/2025
Probability Problems
Binomial: n = 20, p = 0.30
20
Function: 𝑃 𝑋 = 𝑥 = 0.30 (1 − 0.30)
𝑥
Solution: No more than 4 out of 20 such failures are due to
operator error?
𝑃 𝑋 ≤ 4 = 𝑃 𝑋 = 0 + 𝑃 𝑋 = 1 + …+ 𝑃 𝑋 = 4
20
𝑃 𝑋≤4 = 0.30 (1 − 0.30) +…+
0
20
0.30 (1 − 0.30)
4
= 0.2375
Some Special Discrete Probability Distribution
Poisson Distribution
Poisson experiment observing the number of outcomes
occurring during a given spatial or temporal interval.
𝑒 𝜆
𝑃(𝑋 = 𝑥) = ,𝑥
Functional Form 𝑥!
= 0,1,2, . . .
𝐸[𝑋] = 𝜆 𝑉[𝑋] = 𝜆
7
11/02/2025
Some Special Discrete Probability Distribution
Poisson Distribution
Example: The average number of cars in every 50 square
meters radius is 4. What is the probability that 6 cars are
in a span of 50 square meter radius?
Given: 𝜆 = 4, 𝑥 = 6
Solution: 𝑒 4
𝑃(𝑋 = 6) = = 0.1042
6!
Some Special Discrete Probability Distribution
Poisson Distribution
Example: A small coffee shop receives an average of 5
customers per hour. The manager wants to determine
the probability that exactly 3 customers will arrive in a
randomly chosen hour.
Given: 𝜆 = 5 , x = 3
Solution:
𝑃 𝑋=3 = = = 0.14
! !
8
11/02/2025
Some Special Discrete Probability Distribution
Poisson Distribution
Example: A construction site experiences an average of
12 minor equipment failures per month. What is the
probability that in a given month, fewer than 3 failures
occur?
Probability Problems
Poisson: interval is per hectare, 𝝺 = 12
×
Function: 𝑃 𝑋 = 𝑥 =
!
Solution: fewer than 3 failures occur?
𝑃(𝑋 < 3) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2)
𝑒 12 𝑒 12 𝑒 12
= + +
0! 1! 2!
= 0.0005
9
11/02/2025
Continuous Probability Distribution
Normal Distribution
Bell-shaped, area under the curve is 1, P(X=x) ~ 0
𝑃 𝑋 < 𝑥 = ∫ 𝑓 𝑥 need to integrate to find the probability!
There is a simpler way Standard normal transformation
Continuous Probability Distribution
Standard normal transformation
𝑃 𝑋 < 𝑥 = 𝑃 𝑍 < 𝑧 𝑤ℎ𝑒𝑟𝑒 𝑧 =
Common z-values:
P(Z<1.645)= 0.95
P(Z<1.96)= 0.975
P(Z < 2.00) = 0.9772
P (Z< 2.33) = 0.99
10
11/02/2025
Some Special Discrete Probability
Distribution
Normal Distribution Example
The heights of students in a university class
are normally distributed with a mean of 170 cm
and a standard deviation of 8 cm. What is the
probability that a randomly selected student is
taller than 180 cm?
Some Special Discrete Probability Distribution
Normal Distribution Example
Given:
𝝁 =170 cm; 𝝈 = 8 cm; X = 180 cm Find: P[X>180]
𝑿 𝝁
𝒛=
𝝈
𝟏𝟖𝟎 𝟏𝟕𝟎
= 𝟖
= 𝟏. 𝟐𝟓
11
11/02/2025
Some Special Discrete Probability Distribution
Normal Distribution Example
Given:
Given:
𝝁 =170 cm; 𝝈 = 8 cm; X = 180 cm Find: P[X>180]
P[X>180]
= 1-P[Z < (180-170)/8 ]
=1- P[ Z < 1.25]
= 1- 0.8944
= 0.1056
Thus, the probability that a randomly selected student is taller
than 180 cm is 10.56%.
Some Special Discrete Probability Distribution
Normal Distribution Example
DGP University conducts placement examination to all
incoming freshmen ABE. The examination scores of the 1000
examinees last semester were approximately normally
distributed with pop. mean score of 80 and pop. standard
deviation of 5.
What is the probability that randomly chosen student got a
score:
(1) below 70?
(2) above 82?
(3) between 75 and 90?
12
11/02/2025
Some Special Discrete Probability Distribution
Normal Distribution Example
Given: 𝝁=80; 𝝈= 5 Find: (1) P[X<70]
P[X<70]
= P[Z < (70-80)/5 ]
=P[ Z < -2]
= P [ Z > 2]
= 1 – P[ Z < 2]
= 1- 0.9772
= 0. 0228 = 2.28%
Some Special Discrete Probability Distribution
Normal Distribution
Given: 𝝁=80; 𝝈= 5 Find: (2) P[X> 82]
P[X > 82]
= P[Z > (82-80)/5 ]
=P[ Z > 0.4 ]
= 1 – P[ Z < 0.4]
= 1- 0.655 =0. 345 => 34.5%
NOTE: Normal Distribution Example Item (3) will be your
assignment
13
11/02/2025
Probability Problems
It is known that the
mechanical energy
produced using Bevel
Windmills follow the normal
distribution with a mean of 36
and variance of 4. What is the
probability that a Bevel
Windmill will produce:
1. Exactly 40?
2. Less than 32?
Probability Problems
It is known that the mechanical energy produced using
Bevel Windmills follow the normal distribution with a
mean of 36 and variance of 4. What is the probability
that a Bevel Windmill will produce:
1. Exactly 40?
P(X = 40) = 0
2. less than 32?
32 − 36
𝑃(𝑋 < 32) = 𝑃 𝑍 < = 𝑃(𝑍 < −2) = 1 − 𝑃(𝑍 < 2) = ~ 0 . 05
2
14
11/02/2025
Probability Problems
A concrete batching plant produces concrete cylinders
with an average compressive strength of 15 MPa. What
must be the variance of the population such that the
probability of producing a cylinder with a strength of at
least 18 MPa is 0.95?
Given: : 𝝁=15; P(X > 18) = 0.95; 𝝈= ?
Some Special Discrete Probability Distribution
𝝁=15; P(X > 18) = 0.95; 𝝈= ?
Solution:
P[X > 18] = 0.95 P[Z > (18-15)/ 𝝈 ] = 0.95
1- P[ Z < (18-15)/ 𝝈 ] = 0.95
Let a = (18-15)/ 𝝈 ,
1- P[ Z < a ] = 0.95 P [ Z < a] = 0.05
Using the Z table, a = -1.645,
-1.645 = (18-15)/ 𝝈
𝝈 = - 1.8237 𝝈2 = 3.3259
15
11/02/2025
Normal Approximation to the Binomial and
Poisson Distribution
The Normal Approximation is used when Binomial or
Poisson distributions have large values of 𝑛 (for binomial)
or 𝜆 (for Poisson), making them difficult to compute
directly.
Normal Approximation to the Binomial and
Poisson Distribution
A binomial distribution 𝐵(𝑛,𝑝) can be approximated by a
normal distribution 𝑁(𝜇,𝜎 ) when:
n is large (n ≥ 30)
p is not too close to 0 or 1 (generally np ≥ 5 and n(1−p) ≥ 5)
The normal approximation uses:
μ = np
𝜎 = np(1-p)
16
11/02/2025
Normal Approximation to the Binomial and
Poisson Distribution
A Poisson distribution 𝑃(𝜆) can be approximated by a
normal distribution 𝑁(𝜇,𝜎 ) when:
λ (mean number of occurrences) is large (𝜆 ≥ 30).
The normal approximation uses:
μ = 𝜆
𝜎 = 𝜆
Normal Approximation to the Binomial and
Poisson Distribution
Continuity correction
Is an adjustment used when approximating a discrete
probability distribution (such as Binomial or Poisson)
with a continuous normal distribution. Since the
normal distribution deals with continuous values and
the binomial/Poisson distributions deal with whole
numbers (integers), we apply ±0.5 to better
approximate probabilities
17
11/02/2025
Normal Approximation to the Binomial and
Poisson Distribution
Continuity Correction
Discrete Continuous
P(X=a) P(a−0.5<X<a+0.5)
P(X>a) P(X>a+0.5)
P(X≥a) P(X>a−0.5)
P(X<a) P(X<a−0.5)
P(X≤a) P(X<a+0.5)
Probability Problems
A construction company finds that 40% of its concrete
samples fail a strength test. If they test 100 samples, what
is the probability that more than 50 fail?
What is the appropriate distribution?
BINOMIAL
18
11/02/2025
Some Special Discrete Probability Distribution
Binomial Distribution
Given: n =100; p = 0.4 Find: P[X < 50]
Solution:
𝜇 = 𝑛𝑝 = 100 0.4 = 40
𝜎 = 𝑛𝑝 1 − 𝑝 = 40(0.6) = 4.9
P[X > 50], we use X = 50.5
P[X > 50] = 1 – P[Z > 50.5 – 40/4.9]
= 1 – P[Z > 2.14]
= 1 – 0.9838
= 0.0162 so, the probability is 1.62%.
Probability Problems
A highway maintenance team observes an average of
50 potholes per month on a highway section. What is the
probability that fewer than 45 potholes appear next
month?
What is the appropriate distribution?
POISSON
19
11/02/2025
Some Special Discrete Probability Distribution
Poisson Distribution
Given: λ = 50 𝝁 = 50 = 7.07 Find: P[X < 45]
Solution:
P[X < 45], we use X = 44.5
P[X < 45] = P[Z > 44.5 – 50/7.07]
= P[Z < – 0.78]
= 0.2177 so, the probability is 21.77%.
Normal Approximation to the Binomial and
Poisson Distribution
Exponential Distribution
a continuous probability distribution that describes the time
between events in a Poisson point process, where events occur
continuously and independently at a constant rate.
Cumulative Distribution Function:
𝑃 𝑋 ≤𝑥 =1−𝑒
Mean
𝐸 𝑋 =1 𝜆
Variance
𝑉 𝑋 =1
𝜆
20
11/02/2025
Probability Problems
Example: A machine breaks down on average once
every 10 hours. What is the probability that it will last at
least 12 hours before breaking down?
Given: x = 12 hrs. ; λ = 1/10 = 0.1
Solution:
P[x ≥12] = 𝑒 =𝑒 . ( )
= 0.3012
Thus, the probability that the machine lasts at least 12 hours is
30.12%
Probability Problems
Example: Cars arrive at a toll booth at an average rate
of 6 per hour. What is the probability that the next car
arrives within 5 minutes?
Given: x = 5 ; λ = 6/60 = 0.1
Solution:
P[x ≤12] =1 – 𝑒 =1−𝑒 . ( )
= 0.3932
Thus, the probability that the machine lasts at least 12 hours is
39.35%
21
