Ts.

Dr Farm Yan Yan

Mechanical Engineering Programme
School of Engineering and Information Technology
Universiti Malaysia Sabah
Measure of average are
also called as measures
of central tendency

To know how the data dispersed

around the mean, are the data
spread evenly through out the
distribution?

Measure the position to determine

a specific data value fall within the
data set or relative position in
comparison with ither data vaues
 BOXPLOT

Source: Paraskevi et. al., 2019. Highly Multifunctional Dopamine-Functionalized Reduced Graphene Oxide Supercapacitors,
MATTER, vol 1, Issue 6, P1532-1546.

- rGO-1wt% DOPA/Ca+ with 25wt% BANF achieve higher in Ultimate strength & Young’s Modulus but
in shows in high variability.
- rGO has lower in Ultimate strength with 10wt% and 25wt% BANF but lower in variability and
RANDOM VARIABLES
To present an introduction to the theory of probability and to
suggest the role that probability will play in statistical
inference.
Topics
1. The Role of Probability in Statistics
2. Basic of Probability
3. Compound and Complementary Events
4. Conditional Probability
5. Probability Rules for Unions and Intersections
6. Law of Total Probability
7. Bayes Theorem
8. Permutation and Combination
Why do we need to learn
Probability ?
— Learn the pattern
— To make successful/ better decision

— Good sharing on How Is Probability Used in Real Life?

By Andrzej (Andy) Skrzypacz, Professor of Economics
Stanford Graduate School of Business
https://www.youtube.com/watch?v=_sY3ZRxhBaM
Probability
— … of a simple event is a number that measures the
likelihood that the event will occur when the
experiment is performed.
— … is approximated by the proportion of times that the
simple event is observed when the experiment is
repeated a very large number of times.
— … for a simple event E, denoted as P(E).
Probability Rules
— Let E1, E2, E3,… Ei, … Ek be the simple events in a sample
space.
— All simple event probabilities must lie between 0 and 1
— 0 £ P(Ei) £ 1 for i = 1, 2, 3, …, k
— The sum of the probabilities of all the simple events
within a sample space must be equal to 1.
k
å P ( Ei ) = 1
i =1

(See: page 55)

— Complement of an event A is the event that consisting
of all simple events that are NOT in event A. We will
denote the complement of A by Ac. Therefore,
— (A È Ac) = S

— and it results that the sum of the probabilities of

complementary events equals to 1.
— P(A) + P(Ac) = 1
3.2 Basic of Probability
— An experiment is the process of obtaining an observation or taking a
measurement.
— Experiment:
— Toss two coins and observe the up face on each.
— A simple event, E is a basic outcome of an experiment; it cannot be
decomposed into simpler outcomes.
— Simple event:
— Observe HH Sample space: T H
— Observe HT S: {HH, HT, TH, TT}
— Observe TH
— Observe TT
— An event is a specific collection of simple events.
— Event A = observing two same face of coin.

— The sample space, S of an experiment is the collection of all its simple

events.
— Sample space:
— A: {HH, TT}
Example 2:
— Experiment:
— The possible of freeway exit by three vehicles turn left (L) or right
(R) at the end of the exit ramp .
— Simple event:
— Observe E1=LLL; E2=RLL; E3=LRL; E4=LLR; E5=LRR; E6=RLR;
E7=RRL; E8=RRR
— Sample space:
— S: {LLL, RLL, LRL, LLR, LRR, RLR, RRL, RRR}
— Event:
— A=The event that exactly one of the three vehicles turns right
— B= The event that at most one of the vehicles turns right
— C= The event that all three vehicles turn in the same direction
— Sample space:
— A: {RLL,LRL,LLR} ; B= { LLL;RLL;LRL;LLR} ; C={LLL;RRR}
3.3 Compound and Complementary Events
— An event can be viewed as a composition of two or
more other events and is called compound events.
They can be composed by:
— Union of two events A or B (A È B) (ATAU)
— Event that occurs if either A or B, or both, occur on a single
performance of the experiment
— Intersection of two events A and B (A Ç B) (DAn)
— Event that occurs if both A and B occurs on a single
performance of the experiment
Combining Events
— Union àA∪B- A or B
— Intersection à A∩B (A and B)
— Complement of an event àAc ( the set of outcomes
that do not belong to A)
Venn Diagram
— Venn Diagram is a graphical representation to show
the sample space, S, in a closed figure. The close figure
contains a set of points, called sample points, with
each point representing one simple event.
Probability
— Event:
— Event A of observing two same face of coins.
— Sample possibility:
— A: {HH, TT}

— S: {HH, HT, TH, TT}

— We write: P(A)=2/4= 1/2

— The probability of an event A is equal to the sum of the

probabilities of the simple events in event A.
— P(A) = P(observe TT) + P(observe HH)
— =¼+¼=½
Let’s try
— An electrical engineer has on hand two boxes of resistors
with three resistors in each box. The resistors in first box
are labeled 10 Ω. But in fact their resistances are 9, 11 and 12
Ω. The resistors in second box are labeled 20Ω. But in fact
their resistances are 19, 20 and 21 Ω. The engineer chooses
one resistor from each box and determine the resistance of
each.
Let S= { (9, 19), (9,20), (9, 21), (11, 19), (11, 20), (11, 21), (12,
19), (12, 20), (12, 21)}

If A= 1st resistors > 10Ω

B = 2nd resistors < 20 Ω
C = Sum of resistance = 29 Ω

Find the subsets corresponding to events A, B, and C.

Answer:
Let S= { (9, 19), (9,20), (9, 21), (11, 19), (11, 20), (11, 21), (12,
19), (12, 20), (12, 21)}
A
If A= 1st resistors > 10Ω
•(11,20)
B = 2nd resistors < 20 Ω
C = Sum of resistance = 29 Ω •(11,21)
•(12,21)
•(12,20)
B •(12,19)
Find the subsets corresponding to events A, B, and C. (9, 19) • (11,19)
A= { (11,19), (11,20), (11,21), (12,19),(12,20),(12,21)}
B= { (9, 19), (11, 19), (12, 19)}
C
C= {(9,20)}
{(9,20)}
Find the A U B , A n B and B n Ac .

A U B = {(9, 19),(11,19), (11,20), (11,21),(12,19),(12,20),(12,21)}

A n B = {(11, 19), (12, 19)}

A n Bc = { (11,20), (11,21), (12,20),(12,21)}
B n Ac = { (9,19)}
Additional Rules
— When two events A and B are mutually exclusive, the
probability that A or B will occur is
— P( A or B) = P(A) + P(B)
— Event A and B are mutually exclusive if (A Ç B)
contains no simple events.

A B

(A U B)= A + B
P(A U B)= P(A) + P(B) = 1
 A B

A U Bc AnB B U Ac

(A U B)= (A U Bc ) + (A n B) + (B U Ac )
P(A U B)= P(A U Bc ) + P(A n B) + P (B U Ac ) =1
= P(A)+P(B) –P(A and B) = 1
Example 1
Diameter
Length Too Thin OK Too Thick
Too short 10 3 5
OK 38 900 4
Too long 2 25 13

— A rod is sampled at random from this population. What is

the probability that is too short OR too long?
— The total outcome is 1000.
— P(too short)= 18/1000 P( too long)= 40/1000
— P(too short or too long)= 18/1000+40/1000
= 58/1000
 Example 2
Diameter
Length Too Thin OK Too Thick
Too short 10 3 5
OK 38 900 4
Too long 2 25 13

— What is the probability that is either too short or too thick?

P( too short or too thick)= 35/1000
P(too short)=18/1000 ; P(too thick)= 22/1000;
P(too thick and too short)= 5/1000
P( too short or too thick)=
P(too short) + P(too thick)- P(too short and too thick)
18/1000 + 22/10000- 5/1000
= 35/1000
3.5 Conditional Probability
— For case when we need to estimate the probability of
an event A that requires other event B to occur before
hand, conditional probability of the event is involved.
— To find the conditional probability that event A occurs
given that event B occurs, it can be calculated as:
— where P(B) ¹ 0
P( A Ç B) P( A Ç B)
P( A | B) = P( B | A) =
P( B) P( A)
Example 3
Diameter
Length Too Thin OK Too Thick
Too short 10 3 5
OK 38 900 4
Too long 2 25 13

— If we want to get the probability of diameter aluminum rod

in Ok category,
P (diameter OK)= 928/1000= 0.928 (unconditional probability)
— If given that the rod meet the length specification (942),
probability rod meet diameter specification in OK category
as well is 900/942 (Conditional probability)
Example 2
— If the probability that a communication system will have
high fidelity is 0.81 and the probability that it will have high
fidelity and high selectivity is 0.18, what is probability that a
system with high fidelity will also have high selectivity?
P( B|A)
Let’s high fidelity = A; high selectivity = B
Given, P(A)= 0.81 ;P(A n B)= 0.18; P(B | A)= ?
P(B|A)= P(A n B)/P(A) =0.18/0.81 = 2/9 = 0.222
3.8 Bayes Theorem (Refer: Section 2.3)

— Bayes theorem gives us a way of calculating P(E|F)

from a knowledge of P(F|E).
— Example
E = someone’s skin improved
F = they used the new acne cream

P(E|F) = probability that the no. of people who used the

cream given that the subject whose skin improved
P(F|E) = probability that the subject’s skin improved given
that the total people who used the cream
Multiplication rules
— Can be used to find the probability of two or more
event that occur in sequence
— If A and B two events with P(B)≠ 0, then
P(A and B)= P(B)P(A|B)
— If A and B are two events with P(A) ≠ 0, then
P(A and B)= P(A)P(B|A)
— When two events are independent, the probability of
both occurring is
P(A and B)= P(A).P(B)
— If two events are independent, then P(A|B)=P(A) and
P(B|A)=P(B)
Example
— A vehicle contains two engines, a main engine and a back up. The
engine component fails only if both engine fail. The probability that
main engine fails is 0.05, and the probability that the back up engine
fails is 0.1. Assume that the main and back up engines function
independently. What is the probability that the engine component
fails?
— Solution:
P(engine component fails)= P(main engine fails and back up engine fails)
=P(main fails). P(back up fails)
=(0.1) (0.05)
= 0.005
P(B)=P(B|A1)P(A1) + P(B|A2)P(A2)+ P(B|A3)P(A3)
= (0.1)(0.45) +(0.12)(0.35)+(0.15)(0.2)
= 0.117

Bayes’ Rule
Let’s try A
— The Gift Basket department at a local upscale grocery store has premade gift baskets
containing the following combinations in stock.

Cookies Mugs Candy

Coffee 20 13 10
Tea 12 10 12

— Find the probability that:

a) If one basket is chosen at random, it contains coffee or candy;
b) If one basket is chosen at random, it contains tea, given it contains mugs;
c) If one basket is chosen at random, it contains tea and cookies;
d) If three baskets are chosen at random, and not replaced, all of the baskets contain
mugs;
e) If three baskets are chosen at random, and not replaced, none contain mugs;
f) If three baskets are chosen at random, and not replaced, at least one contains mugs.
LET’S TRY B
— An automobile insurance company divides customers into three
categories, good risks, medium risks, and poor risks. Assume that 70%
of the customers are good risks, 20% are medium risks, and 10% are
poor risks. Assume that during the course of a year, a good risk
customer has probability 0.005 of filling an accident claim, a medium
risk customer has probability 0.01, and a poor risk customer has
probability 0.025. A customer is chosen at random.
a) What is the probability that customer is a good risk and has filed a
claim?
b) What is the probability that customer has filed a claim?
c) Given that the customer has filed a claim, what is the probability that
the customer is a good risk?