E3BAIS Chapter 1

Download as ppt, pdf, or txt
Download as ppt, pdf, or txt
You are on page 1of 74

CHAPTER 1

PROBABILITY DISTRIBUTION
 It is concerned with the analysis of random
phenomena. The outcome of a random event cannot be
determined before it occurs, but it may be any one of
several possible outcomes. The actual outcome is
considered to be determined by chance.
 It is the measure of the likelihood that an event
will occur in a Random Experiment(i.e. Whenever we’re
unsure about the outcome of an event, we can talk
about the probabilities of certain outcomes—how
likely they are).
 Experiment: is a trial/process that generates two or
more possible outcomes.
 Sample space/outcome space: The set ALL possible
outcomes of an experiment.
 Event: is any subset of sample space.
Example 1:
Experiment: Toss/Flip a coin once
Sample space: Head, Tail
Event:
Example 2:
Experiment: Toss a coin twice
Sample space: (Head,Head),Head, Tail),(Tail, Head),
(Tail,Tail).
Event:
Experiment: Measuring the time until the bus comes
Sample space: (0, )
Event:
Classical definition of probability:
 Let A be an event and S a sample space, then
 P(A)=n(A)/n(S)
Example 1: What is the probability of getting atmost 2
head in tossing a coin twice? Three times?
Example 2: What is the probability that both coins turn
up the same in rolling a die twice? What is the
probability of getting a sum of 12 in this
experiment?
Example 3: What is the probability of drawing an Ace in
a deck of 52 playing cards, when selection is with
replacement? Without replacement?
 Two events are independent if and only if the
occurrence of the first event does not have an effect
on the probability of occurrence of the second
event(Events A and B are independent if: knowing
whether A occurred does not change the probability of
B). If two events are not independent, then they are
said to be dependent events.
Example: Let A = the event of drawing number 10 in a
deck of 52 playing cards,
B = the event of drawing number 5
 If A and B are chosen without replacement, are they
independent?
 If A and B are chosen with replacement, are they
independent?
NB: If A and B are independent, then P(AnB)=P(A)P(B)
Exercise: Experiment is rolling a die twice; A = first
die lands 1; B = second die shows larger number than
first die; C = both dice show same number. Are A and
Let A and B be two events:
The conditional probability of an event A is the
probability that the event will occur given the
knowledge that an event B has already occurred. This
probability is written P(A|B), notation for
the probability of A given B.
 P(A|B)= P(AnB)/P(B)
NB: If A and B are independent, then P(A|B)= P(A)
Illustrative example:The weatherman might state that
your area has a probability of rain of 40%. However,
this fact is conditional on many things, such as the
probability of…
 …a cold front coming to your area.

 …rain clouds forming.

 …another front pushing the rain clouds away, etc.


 Example: Suppose an individual applying to a college
determines that he has an 80% chance of being
accepted, and he knows that dormitory housing will
only be provided for 60% of all of the accepted
students. The chance of the student being
accepted and receiving dormitory housing is defined
by
P(Accepted and Dormitory Housing) = P(Dormitory
Housing|Accepted)P(Accepted) = (0.60)*(0.80) = 0.48.
Random variable

Definition: A random variable is a variable whose


values are determined by all possible outcomes of a
random experiment (i.e., when the value of a variable
is obtained from the outcome of an experiment, that
variable is said to be random variable).
•It is a quantitative result generated from a random
experiment
•It assigns unique numerical values to each of the
outcomes of an experiment.
• It subjects to randomness, and may take on many
numerical values.
•It is a variable whose future values are uncertain.
Notation
a random variable is denoted by X, and its value is
represented by x
Examples
1.Toss a coin two times. Let X be number of heads
obtained.
Is X a random variable?
S = sample space = { HH, HT, TH, TT}
n(TT) = 0
n(HT)= n(TH)=1
n(HH)=2
Therefore, X = x, x = 0, 1, 2.
outcome TT HT HH
N(outcome 0 1 2
2.Toss),xa coin 8 times. Let X be number of tails
obtained.
X = x, x = 0, 1, 2, 3, 4, 5, 6, 7,8
3. Let X be number of children of a family in A.A.
X = x, x = 0, 1, 2, 3, 4, ------- K
Where k = maximum number of children
4. Let X be the mark of a student in a particular
exam (out of 100)
X = x, 0 ≤ x ≤ 100. – Infinitely many values
5. Let X be the life length in hrs of an electric
bulb.
X = x, 0 ≤ x ≤ k, where k = max. life length
6. Let X = the market share of the product at a
particular time.
7. Let X= the monthly unemployment figures in Ethiopia
over the last 10 years.
8. Let X= the sales of a particular product at a
particular time.
Note
There are two types of random variables: Discrete and
Continuous random variable.
 Discrete random variable is one which may take only on
a countable number of distinct values such as
0,1,2,3,4,...
-Discrete random variable
X: S ---- Z

Examples of discrete random variables:

1.The number of sales transactions made by a company in a


given day
2. The number of defective items in a batch
3.The number of employees attending a training
session/The number of employees leaving the company per
year
4.The number of customers who arrive during a specific
time period in a retail store or a website
5.The number of software bugs found in a Code Review
6. The number of website clicks in a Given Time Period
A continuous random variable is a vriable that assigns
any value in an interval

It is the one which takes an infinite number of


possible values

Continuous random variable


X: S------R
Examples of continuous random variables:
1.The total revenue generated by a company from sales can
be modeled as a continuous random variable, as it can take
on any real value within a certain range
2. Time Spent on Customer Service Calls: The time taken to
resolve customer service calls
3. Interest Rate: When dealing with financial instruments
such as bonds or loans, the interest rate can be treated
as a continuous random variable
Discrete probability function
Definition: Let X be a discrete random variable
with finite number of values: x1, x2, ---- xn., and

the corresponding probabilities

p(xi) = p(X = xi), i = 1, 2,…,n


Then the function p(xi) is called the
probability function of X if the following
conditions are satisfied
i) p(x
n i)≥ 0 for all x

 p ( xi ) = 1
ii) i 1
Example 1

Check if p(x) = 1/4, x = 0, 1, 2, 3. is a probability


function or not.

Example 2

Suppose a variable X can take the values 1, 2, 3,or 4.


The probabilities associated with each outcome are
described by the following table:
Outcome 1 2 3 4
Probability 0.1 0.3 0.4 0.2
Exercise 1
Show that p(x) = x/x+1, x = 0, 1, 2, 3, 4 is not a
probability function.
Exercise 2
Show whether or not the following table satisfies the
properties of discrete probability function, where
X is the number of errors made by a secretary per page.

x P4(x)
0 0.6561
1 0.2916
2 0.0486
3 0.0036
4 0.0001
Discrete probability distribution

The collection of all pairs [xi, p(xi)], i= 1, 2,…


n. is called the probability distribution of the
random variable x.
(i.e. it is a function that associates random
values with their corresponding probabilities.)

This is usually written in the form of a table of x


and p(x)

x x1 x2 x3 - - - xn
P(x P(x1) p(x2) p(x3)- - -- p(xn )
)
.

Example
Toss a coin four times and find the probability
distribution of obtaining heads.
Soln
Let X be number of heads obtained in tossing a coin 4
times; x = 0 1, 2, 3, 4

x 0 1 2 3 4
P(x) 1/16 4/16 6/16 4/16 1/16

Note that p(x) is a probability function


Expected value/Mean and standard deviation
of a discrete random variable

Definition: Let x be a discrete random variable with


the following probability distribution

x x1 x2 x3 - - - xn
P(x) P(x1) p(x2) p(x3) - - - p(xn)

The expected value or mean of the random

variable X, denoted
n
by E(X) or µ , is defined as
x

µx = x
i 1
i p ( xi )
E(X) =
And the variance of x, denoted by
n
x or var(X), is
2

given by

2x = var(X) = ( xi   x ) p ( xi )
2

i 1

or, 
n
 P ( xi ) xi   x
2 2 2
x
i 1
Then the standard deviation of x, denoted by Sx or
s.d, is simply the positive square root of the
variance
n
i.e  x =
s.d(X)=
 (x  
i 1
i x
2
) p ( xi )
Examples
1.Toss a coin 3 times and find the expected number
of tails obtained and its standard deviation

Solution
Let X = number of tails obtained
X = x, x = 0, 1, 2, 3.

x 0 1 2 3

P(x) 1/8 3/8 3/8 1/8


The expected number of tail/s obtained is
3
µx = E(x) = x
i 0
i p ( xi )
= 0X1/8+1X3/8+2X3/8 + 3X1/8

=12/8
= 3/2
= 1.5 tails
Therefore, 1 tail or 2 tails are equally expected
in tossing a con 3 times
n

 2
x = var(x) =  i x p( xi )
( x
i 1
  ) 2

= (0- 3/2)2X1/8 +(1-3/2)2X3/8 +(2-3/2)2X3/8

+(3.3/2)2X1/8

= 3/4
The standard deviation or the fluctuation or
uncertainity from the expected value 1.5 tails is

σx = s.d =Var (x )
= 3/ 4

= 
3/2 tails
2. A study shows that the following is data of the number of
crises that could occur during the day off for the manager of
a business

No of crises (xi) probabilities (p(xi))

0 0.37
1 0.31
2 0.18
3 0.09
4 0.04
5 0.01

Find the expected number of crises and the standard deviation of


the crises during the day off.
Solution
Let x = No of crises during the day off
X = x, x = 0, 1, 2, 3, 4, 5.
5
µx = E(x) = xi p ( xi ) = 1.15 crises
i 0

5
= 1.19
x = s.d =  i x p( xi ) = 1.41 crises
2
( x   )
i 0

Therefore, the expected number of crises during the


day off for the manager is 1.15 crises and the
fluctuation from the mean or expected number of
crises is plus or minus 1.19 crises.
NB:
•The concept of probability distribution is the underlying
foundation of most inferential statistical analysis.
•An understanding of probability distributions is critical in
using quantitative methods such as estimation,
hypothesis testing, regression.

•Distribution means shape or form of data.


•There are few standard shapes of data or distributions.
• Among them, binomial, Poisson and normal
distributions are the most common distributions.
•A random variable X could possibly take any one of these
basic distributions
Binomial Distribution

•It is an example of discrete probability distribution (it


is applicable only for discrete random variable).

•A binomial random variable represents the number of


successes in a fixed number of independent trials,
each with the same probability of success.
•If a random variable is discrete, then the distribution
it takes is a discrete probability distribution.
The binomial distribution is a probability distribution
that models the number of successful outcomes in a
fixed number of Bernoulli trials, where each trial has
two possible outcomes (usually denoted as success
and failure) and the trials are independent and have
the same probability of success.
Examples of binomial random variables in n independent trials

select n students randomly and identify the sex ( male or female


only)
 select n items randomly and check for defectiveness (defective
or non- defective)
 select n patients randomly in a hospital and check whether or
not they survived (die or survive)
 pass or fail; absent or present; etc

Binomial random variables are commonly used in the field of


BAIS to model situations involving binary outcomes or multiple
trials with a fixed probability of success.

In BAIS, you might encounter binomial distributions when


dealing with scenarios involving a fixed number of trials, such as
the success or failure of specific events. In BAIS, the binomial
distribution can have several applications:
1. Error Detection and Correction: In data communication and storage systems, errors can
occur due to various factors. The binomial distribution can be used to model the probability
of correct data transmission or the probability of detecting and correcting errors using
error-detection and error-correction codes.
2. Employee Performance and Evaluation: The binomial distribution can be used to model
the probability of employees meeting specific performance targets or goals. This is
valuable in performance evaluations, incentive programs, and human resource
management.
3. Marketing and Sales: Marketers can use the binomial distribution to analyze the
effectiveness of advertising campaigns, sales calls, or other marketing efforts. By modeling
the probability of success (e.g., conversion rates), they can make data-driven decisions on
resource allocation and campaign strategies.
4.Project Management: In project management and project scheduling, the binomial
distribution can be used to model the probability of tasks being completed on time or
within budget, taking into account uncertainties and risks.
5.Risk Assessment: In risk assessment for information systems and cybersecurity, the
binomial distribution can be used to quantify the likelihood of security breaches or data
breaches occurring and to assess the impact of security measures.
6. Queuing Theory: In the analysis of information systems with queues (e.g., call centers,
server farms, or data centers), the binomial distribution can be used to model the
probability of specific queue lengths or wait times for service requests.
Definition: If a random variable X is binomial in n
independent trials with probability (p) of success and
probability [(1-p) or q] of failure on a single trial,
then the probability function of the random variable X
is called binomial distribution, which is given by
n
P(X = x) = x )p q , x = 0, 1, 2, ---, n.
( x n-x

where, p = p(success),

q = p(failure),

n = number of trials
n!
( nx ) =
nCx =
x!( n  x )!
Note

1. A binomial distribution is identified or specified by two parameters


n and p.

2. If a random variable X is binomial with parameters n and p, then it is


written as X B(n, p)
Examples
1.A study shows that 30% of items produced by a
factory are defective. If a random sample of 4
items are selected, what is the probability that
a) Exactly 2 of them are defective
b) At most 1 is defective

Exercise:
what is the probability that
i) Not less than 2 are non – defective. Ans: 0.3483
ii) At least 1 is non-defective.
Ans: 0.9919
Solution

Let X = number of defective items


n = 4 = number of trials
X = x, x = 0, 1, 2, 3, 4.
Outcomes at each trial are, defective or non-
defective.
Therefore, X is a binomial random variable.
i. e. X B(n, p)
n=4
p = p(success) = p( defective) = 30% = 0.3
q = p( failure) = p( non – defective)=1- p =
0.7
p(X = x) = 4Cx(0.3)x(0.7)4-x, x = 0, 1, 2, 3, 4.
a) p(X =2) = 4C2(0.3)2(0.7)4-2 = 6X0.09X0.49 =
0.2646

b) p(X ≤ 1) = p(X = 0,1) = P(X =0) + p(X=1)


= 4C0(0.3)0(0.7)4-0 +4C1(0.3)1(0.7)4-1
= 0.2401+0.4116
= 0.6517
Example 2. Medical sources show that one in ten
babies admitted to a hospital die of certain
disease. Suppose that a random sample of five
babies are selected from hospitals, what is the
probability that
a) More than 2 babies die
b) at least 1 baby die
c) no baby survives
d) at most 4 babies survive
Solution
Let X = number of babies die
n = 5 – number of trials
X = x, x = 0, 1, 2, 3, 4, 5.
Outcomes at each trial are exactly two, die or
survive
 X  B(n,p)
n= 5, p= p(success) = p( die) = 0.1
q = p(failure) = 1 – p = 0.9
p(X=x) = 5Cx(0.1)x(0.9)5-x , x =0, 1, 2, 3, 4, 5
a) p(X > 2) = p(X = 3,4,5)
= 5C3(0.1)3(0.9)5-3 +5C4(0.1)4(0.9)5-4
+ 5C5(0.1)5(0.9)5-5
= 0.0081+0.00045+0.00001
= 0. 00856
b) p(x≥1) = p(x =1, ,2, 3, 4, 5)

= 1 – p(x<1) = 1 – p(x = 0)
= 1- 5C0(0.1)0(0.9)5-0
= 1 – (0.9)5
= 1 – 0.59049
= 0.4951
c) Let x = number of babies survive
X = x, x = 0, 1, 2, 3, 4, 5.
n=5
p = p(success ) = P(survive) = 0.9
q = p(failure) = p(die) = 1 – p = 0.1
P(X= x) = 5Cx(0.9)x(0.1)5-x, x = 1, 2, 3, 4, 5.
P(x=0) = 5C0(0.9)0(0.1)5-0 = (0.1)5 = 0.00001
d)p(x≤ 4) = 1- p(x> 4) = 1 – p(x = 5) = 1-
5C4(0.9)4(0.1)5-4
= 1 – 0.32805
= 0.67195
Exercises

1. A company produces electronic components, and


on average, 5% of the components are defective. A
quality control team randomly selects 10 components
for inspection. What is the probability that exactly 2 of
the components are defective?

2. A bank receives loan applications, and historically,


80% of the applications are approved. If the bank
receives 20 loan applications, what is the probability
that at most 2 applications are approved?
Expected value and standard deviation of a
binomial random variable

If X is a binomial random variable with parameters


n and p, then the expected value and standard
deviation of X are given by:

µx = E(x) = np

x = s.d = npq
Poisson distribution
•Poisson distribution: is an example of discrete
probability distribution.
•It models the number of events that occur within a
fixed interval of time or space.
A Poisson random variable represents the number
of events occurring in a fixed interval of time or
space.
Examples of Poisson random variable:
1. Let X be number of accidents in one year
X= x, x= 0, 1, 2, ---
 x accidents/year
Event- accident
Unit – year
2. Let X is be number of errors per page
X= x, x= 0, 1, 2, ---
 x errors/page
Event – error
Unit – page

3. Let X be number of customers arriving at a


bank
in one minute
X= x, x= 0, 1, 2, ---
 x customers/minute
Event – arrival of customers
Unit – minute
Etc…
In business administration and information systems (BAIS), Poisson
distributions can model situations where events occur randomly over time or
space. The Poisson distribution has several applications in BAIS. Here are
some examples of how it is used:
1.Website Traffic: In the context of information systems and online
businesses, the Poisson distribution can be used to model website traffic,
such as the number of visitors or page views in a given time interval. This
information is valuable for capacity planning for servers, server allocation,
and website performance optimization.
2.Risk Assessment: Businesses can use the Poisson distribution to assess and
manage risks, particularly in insurance and finance. It is applied to model the
frequency of rare events, such as insurance claims or financial market
fluctuations, to determine appropriate risk mitigation strategies and pricing.
3.Inventory Management: The Poisson distribution can be used to model the
arrival rate of customer orders or the demand for inventory items. By
understanding the distribution of order arrivals, businesses can optimize their
inventory levels, reorder points, and safety stock to ensure that they meet
customer demand while minimizing holding costs.
4.Call Center Management: Consider a call center where calls
arrive randomly. The Poisson distribution can be used to model
the number of calls received in a specific time period. This
information helps in workforce management, determining the
number of operators needed during peak hours, and optimizing
resources.

5.System Failures: The occurrence of system failures or errors in


an information system can be modeled using the Poisson
distribution. This is useful for predicting system reliability,
scheduling maintenance activities, and ensuring the availability of
critical services.

6.Data Arrival in Queuing Systems: Queuing systems, such as


those found in database management or processing job queues,
can use the Poisson distribution to model the rate at which new
data or tasks arrive. This information helps in optimizing system
Let  be average number of events per unit. Then T =
average number of events occurring in T units.

•If X is the average number of events in T units, then X is a


random variable that satisfies Poisson law, which is called the
Poisson distribution, and is given by
 T
e (T ) x
, x = 0, 1, 2, ----
P (X = x) =
x!
where, e = 2. 71826 (irrational
numbers)

e ( )
If T = 1, then, P (X = x) =
x
=, x = 0, 1, 2, ---

x!
Note:

The Poisson distribution is specified by a single


parameter, , and is written as, X P().
Example 1: The average number of customers
entering a retail store in one hour is 20. What is the
probability that exactly 25 customers will enter the
store in the next 2 hours? Answer: 0.0031
Example 2: Suppose a company experiences an
average of 4 transaction errors per day in its financial
records. What is the probability of observing exactly 2
errors in a given day? In 2 days’ time?
Answer: 0.14653; 0.01073
Example 3: Suppose that on a given hour the number
of ships arriving at a port has mean 2.3. What is the
probability that there will be

a) Exactly 3 ships arriving at the port in 2 hrs.


b) At most one ship arrives at the port in one hr.
c) At least 2 ships arrive at the port in 30 minutes.
Example 3: Solution

Let X = number of ships arriving at a port in one hr

X=x, x = 0, 1, 2, ---

 = Average number of ships arriving at a port/hr

= 2.3 ships/hr
 X is a Poisson random variable i.e X P()

e  T (T ) x , x = 0, 1, 2, ----
P (X = x) =
x!
a)  = 2.3
T=2  T = 2.3x2 = 4.6

 T  4 .6 3
P(X = 3) = e (T ) x
e ( 4.6)
=
x! 6
3
0.0101(4.6)
=
6
= 0.164
b)  = 2.3
T=1  T = 2.3

 2.3  2 .3
P(X≤ 1) = p(X = 0,1) e
= (2.3) 0 + e ( 2.3) 1

1 1
= 3.3e-2.3

= 3.3X0.1003
= 0.33099
-

c)  = 2.3
T = 0.5  T = 2.3x0.5 = 1.15

P(X≥ 2) = 1 – p(x < 2) = 1 – p(X =0,1)


 1.15 1
=1 - e  1.15
(1.15) 0
e (1.15)
-
1 1
= 1- e-1.15(1 + 1.15)
= 1 – 0.317X2.15

= 0.31845
Exercise

1.A retail store receives an average of 10 customers per hour


during its peak hours. What is the probability of having at most 5
customers in the next hour?

2.A manufacturing facility experiences an average of 2


equipment failures per week. What is the probability of having
more than 3 failures in 4 weeks’ time?

3.The average number of customer support calls a service desk


receives in 30 minutes is 10. What is the probability that fewer
than 5 calls will be received in the next 30 minutes?

4. The average number of network packets arriving at a server in


one second is 15. What is the probability that the server will
receive no more than 10 packets in the next second?

5. The average number of visits to a website per minute is 8.


What is the probability of having exactly 12 visits in the next
minute?
Note

If X be a Poisson random variable with parameter ,


then the expected value and standard
deviation of X can be shown to be

µx = E(x) = 

2x = var(x) = 

x = s.d =

Poisson approximation to binomial (Assignment)
Continuous probability distributions

A continuous probability distribution is one in which a


continuous random variable X can take on any value
within a given range of values ‒ which can be infinite, and
therefore uncountable.

A continuous random variable X is represented by an


interval,
a ≤ X≤ b or [a, b] – having infinitely many values.
And the probability function is also represented by the
continuous function, f(x), which is called probability
density function (pdf).
Definition: Let X be a continuous random variable
defined over an interval , (-, ) . Then the function
f(x) is called the probability density function of
the random variable x if the following conditions are
satisfied.
i) f (x)  0 for all real x(-, )

ii)
f

( x ) dx = 1.

That is the total area under the curve f(x) and above
x-axis is 1.
NB:
Let f(x) be a probability density function of a
continuous random variable X defined over an
interval [a, b]. Then

a)The probability that x lies in the interval [c, d] is


given by
d

P(c  x  d) =f ( x)dx


c
b) The expected value and standard deviation of X is
also be given as
b
 = E (x) =
 xf ( x)dx
a

And the variance of x is


b

2
V (x) =  =
2 ( x   ) f ( x ) dx
a
Therefore, the standard deviation of x is

=
v(x)
Normal distribution
•It is an example of a continuous probability distribution.
•Normal distribution is a continuous probability distribution that is symmetrical around
its mean, most of the observations cluster around the central peak, and the probabilities
for values further away from the mean taper off equally in both directions.
•The normal distribution, also known as the Gaussian distribution, has numerous
practical applications in business administration and information systems. Here are
some examples:

1. Employee Performance: Performance evaluations and assessments of employees


often assume a normal distribution. This helps in setting benchmarks and identifying
high and low performers within an organization.
2. Financial Analysis: Stock prices and financial returns often follow a normal
distribution pattern. Financial analysts use this distribution to model and predict asset
prices and portfolio performance.
3. Market Research: In market research, the normal distribution is applied to analyze
customer preferences, survey responses, and other data points. This aids in
understanding market trends and making informed business decisions.
4. Quality Control: In manufacturing, the normal distribution is used in statistical
process control to monitor and control the quality of products. Deviations from the
norm may indicate a problem in the production process.
5. Performance Metrics: Metrics such as response time, server load, and network
latency often follow a normal distribution. IT professionals use this information to
optimize system performance and identify potential issues.
6. User Behavior: User engagement metrics, such as the time spent on a website or
the number of clicks, can be modeled using a normal distribution. This aids in user
experience analysis and website optimization.
7. Security Analysis: Anomalies in network traffic or system logs can be detected
by comparing patterns to a normal distribution. Deviations from the norm may
indicate potential security threats or malicious activities.
8. Capacity Planning: The normal distribution is applied in capacity planning to
predict resource requirements, such as server capacity, data storage needs, and
network bandwidth. This helps in ensuring that the IT infrastructure can handle the
expected load.
•A continuous random variable X is said to have a normal
distribution with mean µ and standard deviation, , if its
probability density function (pdf) is given by
1 x  2
1  ( )
f (x) = e 2 
, - < x < 
 2
where, e and  are irrational numbers with
approximate values
e ≈ 2.71826 and  ≈ 3.1416
 and  are population mean and standard deviation
respectively.
Normal distribution is specified by two parameters
µ and, and is written as

X  N( µ, 2 )

The graph of the normal distribution, f(x), is the


familiar bell- shaped curve called normal curve

y
f(x),

x
µ
The normal curve has the following
properties.

It is bell-shaped curve

It is symmetrical about its mean.

The total area below f(x) and above the x- axis is 1

 The area to the right of  = area to left of  = 3. It


is asymptotic to the x-axis.

The mean, median and mode are almost identical

 It is asymptotic to the x-axis.


Definition. A normal distribution with mean zero and
standard deviation one is known as the standard
normal distribution or
Z – distribution with the resulting pdf

1 2
1  z
f (z) = e 2
,-<x<
2
NB:
1, Any continuous random variable X  N(, 2) can
be standardized using the transformation

x 
Z=

i. e, if X  N(, 2), then Z  N(0, 1)

2. A normal table is a standard normal table.


How to read from normal table

After standardization, reading from normal table is


possible if it is in the form
p(0 < Z < a)
where, a = a positive number less than or equal to
3.09
i.e, p(0 < Z < a) = the area under the normal curve
between o and a

P (0< Z < a)

f (z)
0 a
the standard normal table
Examples
- P(0<Z<2.34) = 0.4904
-P(- 1.63< Z < 0)= p(0<Z<1.63)= 0.4484 –
since
the curve is symmetric
-P(Z<1.05) = 0.5 + p(0<Z<1.05) = 0.5 +
0.3531
= 0.8532
-P(Z< -2.35) = 0.5 – p(0<Z<2.35) =0.5 – 0.4906

= 0.0094
-P(-1.43<Z<2.11)= p(0<Z<1.43)
+p(0<Z<2.11)
= 0.4236 +0.4826= 0.9062
-P(-2.34<Z<-1.03) = p(0<Z<2.34) –
p(0<Z<1.03)
= 0.4904 -0.3485= 0.1419
Example
The age of workers of an industry is normally
distributed with mean 35 years and standard deviation
of 5 years.
i)What is the probability that a randomly selected
worker is
a) Less than 40 years of age
b) Between 28 and 37 years of age
c) at least 42 years of age
ii) Find the age
a)Below which 80% of workers have it
b) Above which 60% of workers have it
Solution
Let X = the age of the selected worker
X = x, 18 ≤ X ≤ 60 – continuous random variable.
But X  N(, 2) – given

i) a) p(X < 40) = p( x   40  35


 ) = P(Z < 1)
 5
= 0.5 +p(0<Z<1)
= 0.5 + 0.3413
= 0.8413
p(28<X<37)= p( 28  35  x    37  35 )
5  5
= p(-
1.4<Z<0.4)
= p(0<Z<1.4) +p(<Z<0.4)
= 0.4192 + 0.1554 =
0.5746
c) p(X≥ 42) = p(
x  42  35
(  )
 5
= p(Z≥1.4)= 0.5 – p(0<Z<1.4)
= 0.5 – 0.4192 = 0.0808
ii) a) Let xo = the age below which 80% of workers
have it

0.3
0.5 0.2
= 35 x0
0.5 0.3
0.2

= 0 x 0  35
5
 p(0 < Z < x 0  35 ) = 0.3
5
 x 0  35 = 0.84
5
 xo = 35 +0.84X5 = 39.2
years
b)Let xo = the age above which 60%
of workers have it

0.1
0.4 0.5

xo = 35

0.1 0.5
0.4
x 0  35
 ( )= 0
-5
x0  35
p(-( )< Z < 0) = 0.1
5
 -( x 0  35 ) = 0.25
5
 x 0  35
= - 0.25
5
 xo = 35 – 0.25X 5 = 33.75 years
1. The salary of workers of an industry is normally distributed
with mean salary of $420 and standard deviation of $55. If any
one worker from the industry is selected randomly,
i) What is the probability that he or she has salary of
a) More than $450 b) Less than $300 c) Between $380 and
$490
ii) What is the salary
a) Below which 5% of workers have it

b) Above which 35% of workers have it

2.The average monthly expense on office supplies for a company


is $5,000, with a standard deviation of $800. Assuming the
expense follows a normal distribution, what is the probability that
the company's monthly office supply expense will be between
$4,200 and $5,800?

3.An investment firm is analyzing the monthly returns of a


certain stock. The returns follow a normal distribution with a
mean of 1.5% and a standard deviation of 2.2%. What is the
probability that the stock will have a negative return in the next
month?
4.An auditing firm is investigating the distribution of purchase
amounts in a dataset to identify potential fraudulent
transactions. The purchase amounts are normally distributed
with a mean of $500 and a standard deviation of $100. What
percentage of transactions have purchase amounts exceeding
$700?

Normal approximation to binomial


(Assignment)
THE END OF CHAPTER ONE

You might also like