PROBABILITY DISTRIBUTION

Probability distributions are essential tools in engineering for modeling and

analyzing various processes and systems. Engineers use these distributions to assess
the reliability of components, quality control in manufacturing, and many other real-
world applications. Understanding these distributions allows engineers to make
data-driven decisions and improve the efficiency and safety of their designs and
processes.

Bernoulli Distibution
The Bernoulli distribution is a discrete probability distribution that models a random
experiment with two possible outcomes: success (usually denoted as 1) and failure
(usually denoted as 0). The distribution is characterized by a single parameter, p,
which represents the probability of success.
P( X = x) = p x q1− x ; x = 0,1

Binomial Distribution.
The binomial distribution is a generalization of the Bernoulli. Suppose we repeat a
Bernoulli trial/ experiment several times, say n times and also suppose we are
interested in the number of successes out of the n attempts.
Let X denotes the number of successes. Obviously, the possible values of X are 0,
1, 2 ,…., n. X is a random variable and the probability law which describes the
probability behaviour of X is called the Binomial distribution
Properties of Binomial Distribution
(a). There is a fixed number, n of trials.
(b). The trials are independent.
(c). Only 2 outcomes say ‘’success’’ and ‘’failure’’ are possible at each trial.
(d). The probability, p of success is constant at every trial.
(e). The binomial random variable X, is the number of successes that occur in n trials.

𝑓(𝑥) =
(𝑛𝑥)𝑝 𝑥 (1
− 𝑝)𝑛−𝑥 , 𝑥 = 0,12, … . . 𝑛
{
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
The Mean and Variance of Binomial Distribution.
 𝑚𝑒𝑎𝑛 = 𝑛𝑝 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 𝑛𝑝(1 − 𝑝)

Now let w=x-1 and m=n-1. We see that m-w=n-x. We can now rewrite the
summation as

We now see that the summation is the sum over the complete pmf of a binomial
random variable distributed Bin(m, p). This is equal to 1 (and can be easily verified
using the Binomial theorem). Therefore, we have

Example 1.
A fair coin is tossed 4 times. Let X be the number of heads that appear.
(a). Obtain the probability distribution of X.
(b). Verify that (i). E[X] = np (ii). Var(X) = np(1-p).
Solution.
1
𝑛 = 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑡𝑟𝑖𝑎𝑙𝑠 𝑝 = 𝑝𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑜𝑓 𝑔𝑒𝑡𝑡𝑖𝑛𝑔 𝑎 ℎ𝑒𝑎𝑑 =
2
1 1
1−𝑝=1− =
2 2
1 1 𝑥 1 4−𝑥
𝑋 𝑖𝑠 𝑎 𝐵𝑖𝑛𝑜𝑚𝑖𝑎𝑙 (4, ) 𝑤𝑖𝑡ℎ 𝑝𝑑𝑓 𝑓(𝑥) = (𝑥4) ( ) ( ) 𝑥 = 0,1,2,3,4
2 2 2
1 0 1 4 1 4 1
𝑓(0) = (40) ( ) ( ) = ( ) =
2 2 2 16
1 1 1 3 1 4 4
𝑓(1) = (41) ( ) ( ) = 4 ( ) =
2 2 2 16
 1 2 1 2 4 .3 1 4 6
𝑓(2) = (42) ( ) ( ) = ( ) = 16
2 2 2 .1 2
1 3 1 1 4 .3 .2 1 4 4
𝑓(3) = (43) ( ) ( ) = ( ) = 16
2 2 3 .2 .1 2
4 1 4 1 0 1 4 1
𝑓(4) = (4) (2) (2) =( ) =
2 16
Thus the probability distribution of X is as follows;
X 0 1 2 3 4 Total
f(x) 1 4 6 4 1 1
16 16 16 16 16

(b). (i). To verify E[X] = np

1 1
𝑋 𝑖𝑠 𝑎 𝐵𝑖𝑛𝑜𝑚𝑖𝑎𝑙 (4, ) . 𝑇ℎ𝑒𝑛 𝑅𝐻𝑆 = 𝑛𝑝 = 4 ( ) = 2
2 2
1 4 6 4 1 32
𝐿𝐻𝑆 = 𝐸[𝑋] = ∑ 𝑥𝑓(𝑥) = 0 ( ) + 1 ( ) + 2 ( ) + 3 ( ) + 4 ( ) = = 2
16 16 16 16 16 16
LHS = RHS =2 verified.
(b). (ii). To verify Var(X) = np(1-p).
1 1 1
𝑤𝑖𝑡ℎ 𝑛 = 4, 𝑝 = , 1 − 𝑝 = 1 − =
2 2 2
1 1
𝑇ℎ𝑒𝑛 𝑅𝐻𝑆 = 𝑛𝑝(1 − 𝑝) = 4 ( ) ( ) = 1
2 2
By the definition of variance, we have 𝐿𝐻𝑆 = 𝑉𝑎𝑟(𝑋) = 𝜎 2 = 𝐸[𝑋 2 ] − (𝐸[𝑋])2
1 4 6 4 1 80
𝐸[𝑋 2 ] = ∑ 𝑥 2 𝑓(𝑥) = 02 ( ) + 12 ( ) + 22 ( ) + 32 ( ) + 42 ( ) = = 5
16 16 16 16 16 16
𝑉𝑎𝑟(𝑋) = 𝜎 2 = 𝐸[𝑋 2 ] − (𝐸[𝑋])2 = 5 − 22 = 1
LHS = RHS = 1 verified.
Example 2.
It is known that two out of every ten bolts produced by a machine are defective. In
a pack of six bolts, calculate the probability that:
(a). exactly two bolts are defective (b). not more than two bolts are defective
(c). at least two bolts are defective (d). between two and four bolts are defective
(e). All the bolts are defective.
Solution.
2 1
Let X be the number of defective bolts in a pack of 6 bolts. 𝑛 = 6, 𝑝 = =
10 5

1 4
1−𝑝 =1− =
5 5
 1
𝑋 𝑖𝑠 𝐵𝑖𝑛𝑜𝑚𝑖𝑎𝑙(𝑛 = 1, 𝑝 = ) and the probability distribution function is
5
1 𝑥 4 6−𝑥
𝑓(𝑥) = (𝑥6) ( ) ( ) 𝑥 = 0,1,2,3,4,5,6. (a).
5 5
p(exactly 2 bolts are defective)
1 2 4 4 6 .5 (44 ) 7680 768
𝑓(𝑥 = 2) = 𝑓(2) = (62) ( ) ( ) = = =
5 5 2 .1 (56 ) 31250 3125
(b). p(not more than 2 bolts are defective)
1 0 4 6 1 1 4 5 768
𝑓(𝑥 ≤ 2) = 𝑓(0) + 𝑓(1) + 𝑓(2) = (60) ( ) ( ) + (61) ( ) ( ) + =
5 5 5 5 3125
4 6 45 768 4096 6144 768 14080
(5) + 6 56 + 3125 = 15625 + 15625 + 3125 = 15625
(c). p(at least 2 bolts are defective)
4096 6144 240
𝑓(𝑥 ≥ 2) = 1 − 𝑓(𝑥 < 2) = 1 − 𝑓(0) − 𝑓(1) =1− − =
15625 15625 15625
(d). p(between 2 and 4 bolts are defective)
𝑓(2 ≤ 𝑥 ≤ 4) = 𝑓(2) + 𝑓(3) + 𝑓(4)
768 1 3 4 3 1 4 4 2 768 6 .5 .4 (4)3 6 .5 .4 .3 (4)2
= + (63) ( ) ( ) + (64) ( ) ( ) = + (5)6
+
3125 5 5 5 5 3125 3 .2 .1 4 .3 .2 .1 (5)6
768 1280 240 5360
= + + =
3125 15625 15625 15625
(e). p(all the bolts are defective)
6 1 6 4 0 1 6 1
𝑓(𝑥 = 6) = 𝑓(6) = (6) (5) (5) =( ) =
5 15625

Example 3.
Find the probability of obtaining exactly 12 sixes in 20 throws of a die.
Solution.
1 5
𝑥 = 12, 𝑛 = 20, 𝑝 = , 1 − 𝑝 =
6 6
𝑛 𝑥
𝑓(𝑥) = (𝑥 )𝑝 (1 − 𝑝)𝑛−𝑥 , 𝑥 = 0,12, … . . 𝑛
20 1 12 5 8
𝑓(12) = (12) ( ) ( )
6 6

Example 4.
Find the probability of obtaining exactly 4 heads in 10 throws of a coin.
Solution.
1 1
𝑥 = 4 , 𝑛 = 10, 𝑝 = , 1 − 𝑝 =
2 2
𝑛 𝑥
𝑓(𝑥) = (𝑥 )𝑝 (1 − 𝑝)𝑛−𝑥 , 𝑥 = 0,12, … . . 𝑛
10 1 4 1 6
𝑓(4) = ( 4 ) (2) (2)
Example 5.
An engineering experiment has 80% probability of success. If the experiment is
repeated 5 times, find the probability of obtaining: (i). No success (ii). No failure
(iii). Two successes and three failure.
Solution
Let X denotes the number of times he hits the target. Then X has a binomial
random variable with n = 5 and p = 0.8, 1 – p = 0.2
𝑓(𝑥) = (𝑥5)(0.8)𝑥 (0.2)5−𝑥 𝑥 = 0, 1, 2, 3, 4, 5.
(i). 𝑓(𝑥 = 0) = (50)(0.8)0 (0.2)5 = 0.00032
(ii). 𝑓(𝑥 = 5) = (55)(0.8)5 (0.2)0 = 0.32768
(iii). 𝑓(𝑥 = 2) = (52)(0.8)2 (0.2)3 = 0.0512
Exercise 1
In an aircraft maintenance inspection, there are 15 different components that have a
90% chance of being in good condition. What is the probability that at most 12
components are in good condition?

B. The Poisson distribution.

The Poisson distribution is often referred to as the distribution of rare events. The
events that follow the Poisson distribution often occur in continuous space or time
intervals. Such events, generally speaking must satisfy the following conditions:

(1). The events must occur randomly.

(2). The events must occur independently.
(3). The events must occur singly
(4). The events must occur uniformly in a given space or time interval.
(5). The Poisson random variable, X is the number of events that occur in a space or time interval
of fixed size.
Examples of random variables that follow the Poisson distributions are as follows.
(1). The number of misprints per page of a book.
(2). The number of people affected by an epidemic in a given region or a locality.
(3). The number of cars that pass through a university gate every five minutes.
𝑒 −𝜆 𝜆𝑥
The pdf of X is 𝑓(𝑥) = { , 𝑥 = 0, 1, 2, 3, … …
𝑥!
0 𝜆>0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
λ = the average number of times the random event occurs in a specified interval.
While is the base of a natural logarithm.
In Poisson random variable, we are looking for cases where there are relatively few
successes during the time duration considered and it is assumed that the event
occurring is uniformly distributed over the entire time period under consideration.

The mean and variance of the Poisson Distribution.

Mean

The Variance
We derive the variance using the following formula:

We have already calculated E[X] above, so now we will calculate E[X2] and then
return to this variance formula:

The first sum is E[X]=λ and the second we also calculated above to be 1.

Returning to the variance formula we find that

Example1 .
The average number of days school is closed due to strike in a particular state is 4.
What is the probability that the school will close for 6 days.
Solution.
46 𝑒 −4
𝜆 = 4, 𝑥 = 6 𝑓(4 , 6) = = 0.1042
6!

Example 2.
The number of accidents occurring on a bridge in a year has a Poisson with mean
of 3. Compute the probability that in a year;
(i). Only one accident occurred (ii). At most one accident occurred. (iii). At least
one accident occurred.
Solution.
Let X = The number of accidents occurring on a bridge in a year Then X follows a
Poisson distribution with parameter λ, and its pdf given that the mean of X = E[X]
𝑒 −33𝑥
= 3 accidents 𝑓(𝑥) = , 𝑥 = 0, 1, 2, 3, … …
𝑥!
(i). Probability(Only one accident occurred):
𝑒 −3 31
𝑓(𝑥 = 1) = = 3𝑒 −3 = 0.149
1!
(ii) Probability(At most one accident occurred.):
𝑓(𝑥 ≤ 1) = 𝑓(𝑥 = 0) + 𝑓(𝑥 = 1)
𝑒 −3 30 𝑒 −3 31
= + = 𝑒 −3 + 3𝑒 −3 = 0.199
0! 1!
(iii) Probability(At least one accident occurred.):
𝑓(𝑥 ≥ 1) = 𝑓(𝑥 = 1) + 𝑓(𝑥 = 2) + ⋯
𝑓(𝑥 ≥ 1) = 1 − 𝑓(𝑥 < 1) = 1 − 𝑓(𝑥 = 0)
𝑒 −3 30
𝑓(𝑥 ≥ 1) = 1 − = 1 − 𝑒 −3 = 0.95021
0!

Example 3.
It is known that 3 cars, on the average pass through a university gate every 5
minutes. What is the probability that four or more cars will pass through the gate in
a given 5 – minute interval?
Solution.
Let X = number of cars that pass through the gate every 5 minutes. Then X follows
a Poisson distribution with parameter λ, and its pdf given that the mean of X =
𝑒 −3 3𝑥
E[X] = 3 cars 𝑓(𝑥) = , 𝑥 = 0, 1, 2, 3, … …
𝑥!
The required probability is: p(4 or more cars pass through the university gate in a
given 5 – interval)
𝑓(𝑥 ≥ 4) = 1 − 𝑓(𝑥 < 4) = 1 − [𝑓(0) + 𝑓(1) + 𝑓(2) + 𝑓(3)]
𝑒 −3 30 𝑒 −3 31 𝑒 −3 32 𝑒 −333 𝑒 −3
=1−[ + + + ] = 1− [6 + 18 + 27 + 27] = 0.35
0! 1! 2! 3! 6

Poisson approximation to Binomial.

We use Poisson distribution to approximate Binomial when n ⇢ ∞ and p ⇢ 0.
Example1
If a probability is 0.0001 that any one passenger of a certain sub-way train will be
robbed. What is the probability that 10 of the next 50,000 passengers will be
robbed?
Solution.
𝑝(10 𝑠𝑢𝑐𝑐𝑒𝑠𝑠𝑒𝑠 𝑖𝑛 50,000)
𝐵𝑖𝑛𝑜𝑚𝑖𝑎𝑙(𝑥 = 10, 𝑛 = 50,000, 𝑝 = 0.0001) ≈ 𝑃𝑜𝑖𝑠𝑠𝑜𝑛(10, 5)
𝐸[𝑋] = 𝑛𝑝 = 50,000 × 0.0001 = 5 = 𝜆
510 𝑒 −5
𝑓 (10 , 5) = = 0.018
10!

Example 2.
In a manufacturing company, the probability that any one call is wrongly
connected is 0.004. For a day when 1500 independent calls are connected, find the
probability that five wrong connections are made.
Solution.
𝑝 = 0.004 𝑛 = 1500 𝜆 = 𝑛𝑝 = 0.004 × 1500 = 6.
𝑒 −6 6𝑥
𝑓(𝑥 ) =
𝑥!
𝑒 −6 65
𝑓 (5) = ≈ 0.1606
5!

Classwork
The number of alpha particles emitted per minute by a radioactive substance is
said to follow a poisson distribution with parameter 𝜆 equals 5 alpha particles per
minute. Obtain the probability that
i. Exactly 4 alpha particles are emitted in an hour
ii. Less than 4 alpha particles are emitted in an hour
iii. More than 5 alpha particles are emitted in an hour.
C CONTINUOUS PROBABILITY DISTRIBUTIONS.
1. Continuous Uniform Distribution.
The continuous uniform distribution models any random variable that is equally
likely to take any value in a given interval say [a, b].
1
𝑎<𝑥<𝑏
𝑓(𝑥) = {𝑏−𝑎
0 𝑒𝑙𝑠𝑒𝑤ℎ𝑒𝑟𝑒
Properties.
𝑏 𝑏 𝑑𝑥 1 𝑏 1 𝑏
∫𝑎 𝑓(𝑥)𝑑𝑥 = ∫𝑎 𝑏−𝑎 = 𝑏−𝑎 ∫𝑎 𝑑𝑥 = 𝑏−𝑎 𝑥| = 1
𝑎
The mean is
𝑏 𝑏 𝑥 𝑑𝑥 1 𝑏 1 𝑥2 𝑏 𝑎+𝑏
𝐸[𝑋] = ∫𝑎 𝑥𝑓(𝑥)𝑑𝑥 = ∫𝑎 = ∫ 𝑥𝑑𝑥 = | =
𝑏−𝑎 𝑏−𝑎 𝑎 𝑏−𝑎 2 𝑎 2
The variance is
𝑏 𝑏 𝑥 2 𝑑𝑥 1 𝑏 2 1 𝑥3 𝑏 𝑏 3 −𝑎3
𝐸[𝑋 2 ] = ∫𝑎 𝑥 2 𝑓(𝑥)𝑑𝑥 = ∫𝑎 = ∫ 𝑥 𝑑𝑥 = | =
𝑏−𝑎 𝑏−𝑎 𝑎 𝑏−𝑎 3 𝑎 3(𝑏−𝑎)
𝑏 3 −𝑎 3 (𝑏−𝑎)(𝑏 2 +𝑎𝑏+𝑎 2 ) 𝑏 2 +𝑎𝑏+𝑎 2
𝐸[𝑋 2 ] = = =
3(𝑏−𝑎) 3(𝑏−𝑎) 3
𝑏2 +𝑎𝑏+𝑎2 𝑎+𝑏 2 (𝑏−𝑎)2
𝑉[𝑋] = 𝐸[𝑋 2 ] − (𝐸[𝑋]) =2
−( ) =
3 2 12

Example.
Let X be a random variable whose pdf is
1
−1≤𝑥 ≤1
𝑓(𝑥) = {2
0 𝑜𝑡ℎ𝑒𝑟𝑤𝑖𝑠𝑒
Obtain (a). E[X] (b). E[X2] (c). V[X]
Solution.
(a). By definition of the mean of X.
𝑏 1 1 1 1 1 𝑥2 1 1
𝐸[𝑋] = ∫𝑎 𝑥𝑓(𝑥)𝑑𝑥 = ∫−1 𝑥 ( ) 𝑑𝑥 = ∫−1 𝑥𝑑𝑥 = [ ] = [12 − (−1)2 = 0
2 2 2 2 −1 4
(b). By definition of E[X2]
𝑏 1 1 1 1 1 𝑥3 1 1
𝐸[𝑋 2 ] = ∫𝑎 𝑥 2 𝑓(𝑥)𝑑𝑥 = ∫−1 𝑥 2 ( ) 𝑑𝑥 = ∫−1 𝑥 2 𝑑𝑥 = [ ] = [13 −
2 2 2 3 −1 6
(−1)3 ]
2 1
𝐸[𝑋 2 ] = =
6 3
(c). By the definition of the variance of X.
1 1
𝑉[𝑋] = 𝐸[𝑋 2 ] − (𝐸[𝑋])2 = − 0 =
3 3
2. The Normal Distribution.
It is the most important continuous distribution. The range of X is the real line.
The probability Distribution function is as follows
1 𝑥−𝜇 2
1 − ( )
𝑓 (𝑥 ) = 𝜎 𝑒 2 𝜎 − ∞ < 𝑥 < ∞.
√2𝜋
General properties.
1. 𝐸[𝑋] = 𝜇 𝑉[𝑋] = 𝜎 2
2. The pdf is completely specified when 𝜇 𝑎𝑛𝑑 𝜎 2 are known.
3. 𝑊ℎ𝑒𝑛 𝜇 = 0 𝑎𝑛𝑑 𝜎 2 = 1 X has a standard normal distribution. Thus the pdf
of X becomes
1 2
1
𝑓(𝑥) = 𝑒 −2𝑥 − ∞ < 𝑥 < ∞.
√2𝜋
The importance of the standard normal distribution is the fact that it is tabulated.
4. f(x) is symmetrical about the point µ.
𝑥−𝜇
5. If X has a normal distribution with mean µ and variance σ2 then has a
𝜎
standard normal
distribution.
The graph of the normal distribution (which is bell- shaped) is called the normal
curve.

The normal curve has the following characteristics:

1. It is symmetrical about a vertical axis through its mean.
2. All the measures of central tendency – mean, median and mode are equal.
3. It is bell- shaped and extends indefinitely in both directions. It approaches the
horizontal axis but never touches it. That is it is asymptotic to the x- axis.
4. The total area under the curve and above the x –axis is equal to 1. Hence the
area to the left is 0.5 and the one to the right is 0.5.
The physical shape of the graph of this distribution is equally interesting. It is
shown as:
The diagram shows that if a set of measurements follows a normal distribution
with mean µ and variance σ2, then about 68% of those measurements will lie
within one standard deviation of the mean. 95% will lie within two standard
deviations and about 99% will lie within three standard deviations of the mean.
An important case of the normal distribution arises if 𝜇 = 0 𝑎𝑛𝑑 𝜎 2 = 1. This
special case iis called the standard normal distribution and is usually denoted as
𝑍~ 𝑁(0, 1).
The standard normal variable retains the properties of symmetry (about zero) and
is still bell –shaped. It is also important to note that if X has a normal N(µ, σ2),
𝑥−𝜇
then 𝑍 = has a standard normal distribution 𝑍~𝑁(0, 1).
𝜎
Example1.
Use the standard normal table to find the probability Z < 1.83
Solution.
Less than is to the left. From the table 1.8 under 0.03 = 0.9664
Example2.
Find the probability Z > 1.83
Solution.
𝑝(𝑍 > 1.83) = 1 − 𝑝(𝑍 < 1.83) = 1 − 0.9664 = 0.0336
Example3.
Find the probability p( 1.50 < Z < 1.83)
Solution.
𝑝(1.50 < 𝑍 < 1.83) = 𝑝(𝑍 < 1.83) − 𝑝(𝑍 < 1.50) = 0.9664 − 0.9332 =
0.0332
Example4.
Find the area under the normal curve for (a). Z > 1.53 (b). Z < 1.53 (c). 1 < Z <
1.53 (d). – 1 < Z < 1.53
Solution.
(a). 𝑝(𝑍 > 1.53) = 1 − 𝑝(𝑍 < 1.53) = 1 − 0.9370 = 0.0630
(b). 𝑝(𝑍 < 1.53) = 0.9370
(c). 𝑝(1 < 𝑍 < 1.53) = 𝑝(𝑍 < 1.53) − 𝑝(𝑍 < 1) = 0.9370 − 0.8413 =
0.0957
(d). 𝑝(−1 < 𝑍 < 1.53) = 𝑝(𝑍 < 1.53) − 𝑝(𝑍 < −1) = 0.9370 − 0.1587 =
0.7783
Example.
(a). p(Z < 2.78) (b). p(Z > 1.62) (c). p(1.30 < Z < 3.40) (d). p(Z < - 0.86)
(e). p(Z > - 1.76) (f). p(- 3.10 < Z < - 1.15).
Solution.
(a). 𝑝(𝑍 < 2.78) = 0.9973
(b). 𝑝(𝑍 > 1.62) = 1 − 𝑝(𝑍 < 1.62) = 1 − 0.9474 = 0.0526
(c). 𝑝(1.30 < 𝑍 < 3.40) = 𝑝(𝑍 < 3.40) − 𝑝(𝑍 < 1.30) = 0.9997 − 0.9032 =
0.0965
(d). 𝑝(𝑍 < −0.86) = 0.1949
(e). 𝑝(𝑍 > −1.76) = 1 − 𝑝(𝑍 < −1.76) = 1 − 0.0392 = 0.9608
(f). 𝑝(−3.10 < 𝑍 < −1.15) = 𝑝(𝑍 < −1.15) − 𝑝(𝑍 < −3.10) = 0.1251 −
0.0010 = 0.1241
Example .
Students’ score in a mathematics examination are normally distributed with mean
75% and standard deviation 10%. Find the probability that a student selected at
random scores: (a). less than 60% (b). above 80% (c). between 70% and 90%.
Solution.
Let X = students’ scores in the mathematics examination. 𝑋 ~𝑁𝑜𝑟𝑚𝑎𝑙(75, 100)
𝑋−𝜇 𝑋−75
𝜇 = 75, 𝜎 2 = 100, 𝜎 = 10. . 𝑆𝑖𝑛𝑐𝑒 𝑍 = =
𝜎 10
(a). Required probability is p(X < 60)
𝑋−75 60−75
𝑊ℎ𝑒𝑛 𝑋 = 60, 𝑍 = = = −1.50
10 10
𝑝(𝑋 < 60) = 𝑝(𝑍 < −1.50) = 0.0668.
Thus the probability that a student selected at random will score less than 60% is
0.0668.
(b). Required probability is p(X > 80)
𝑋−75 80−75
𝑊ℎ𝑒𝑛 𝑋 = 80, 𝑍 = = = 0.50
10 10
𝑝(𝑋 > 80) = 𝑝(𝑍 > 0.50)
𝑝(𝑍 > 0.50) = 1 − 𝑝(𝑍 < 0.50) = 1 − 0.6915 = 0.3085
Thus the probability that a student selected at random will score above 80% is
0.3085.
(c). Required probability is p(70 < X < 90)
𝑋−75 70−75
𝑊ℎ𝑒𝑛 𝑋 = 70, 𝑍 = = = −0.50
10 10
𝑋−75 90−75
𝑊ℎ𝑒𝑛 𝑋 = 90, 𝑍 = = = 1.50
10 10
𝑝(70 < 𝑋 < 90) = 𝑝(−0.50 < 𝑍 < 1.50)
𝑝(−0.50 < 𝑍 < 1.50)
𝑝(−0.50 < 𝑍 < 1.50) = 𝑝(𝑍 < 1.50) − 𝑝(𝑍 < −0.50) = 0.9332 − 0.3085 =
0.6247.
Thus the probability that a student selected at random will score between 70% and
90% is 0.6247.
Example.
In a statistics examination, the mean score of 400 students is 78% and the standard
deviation is 10%. How many students have scores:
(a). more than 70% (b). less than 90% (c). between 70% and 90% ?
Solution.
𝑋−𝜇 𝑋−78
𝜇 = 78, 𝜎 = 10, 𝑛 = 400 𝑋 ~ 𝑁(78, 100) 𝑍 = =
𝜎 10
70−78 8
(a). Required probability is p( X > 70) 𝑋 = 70, 𝑍 = = − = −0.8
10 10
𝑝(𝑋 > 70) = 𝑝(𝑍 > −0.80)
𝑝(𝑍 > −0.80) = 1 − 𝑝(𝑍 < −0.80) = 1 − 0.2119 = 0.7881
The number of students that have scores more than 70% is 𝑛𝑝 = 400 ×
0.7881 ≈ 315.
90−78 12
(b). Required probability is p( X < 90) 𝑋 = 90, 𝑍 = = = 1.2
10 10
𝑝(𝑋 < 90) = 𝑝(𝑍 < 1.2) = 0.8849
The number of students that have scores less than 90% is 𝑛𝑝 = 400 × 0.8849 ≈
354.
(c). Required probability is p(70 < X < 90)
70−78 8
𝑊ℎ𝑒𝑛 𝑋 = 70, 𝑍 = = − = −0.8
10 10
90−78 12
𝑊ℎ𝑒𝑛 𝑋 = 90, 𝑍 = = = 1.2
10 10
𝑝(70 < 𝑋 < 90) = 𝑝(−0.8 < 𝑍 < 1.2)
𝑝(−0.8 < 𝑍 < 1.2) = 𝑝(𝑍 < 1.2) − 𝑝(𝑍 < −0.8) = 0.8849 − 0.2119 = 0.673
The number of students that have the scores between 70% and 90% is
𝑛𝑝 = 400 × 0.673 ≈ 269.
Exercise.
The concordant reading of several trials of an experiment follows a normal
distribution with mean of 300cm and standard deviation of 60cm. What is the
probability that a randomly selected trial is (a). greater than 360cm? (b). is between
150cm and 400cm?