Statistical Methods

Probability and Random Variables

PAWAN SINGH
 Basic Concepts
 Experiment
 A process of observation whose outcome is not
known in advance with certainty.
 e.g. Single throw of a 6-sided die.
 e.g tossing a single coin
 Sample space (S)
 Set of all possible outcomes of the experiment.
 e.g. S={1,2,3,4,5,6}
 e.g S= {H,T}
 Event
 A collection of outcomes; a subset of S.
 e.g. A={2,4,6}, B={3}.
Event Operations
 Union of A and B (A  B)
 outcomes that belong to either A or B or
both.
 Intersection of A and B (A  B)
 outcomes that belong to both A and B.
 Complement (Ā)
 All outcomes in S that are not in the particular
event.
 Mutually Exclusive Events
 A and B are mutually exclusive (i.e. disjoint) if
(A  B)=.
Venn Diagrams
Tree diagram
 This is a useful device to build a sample space
and to calculate probabilities of simple events
and events.
 Example: A automobile consultant records fuel type
and vehicle type for a sample of vehicles; 2 Fuel types
(Gasoline, Diesel) and 3 Vehicle types (Truck,
SUV)
Car, e1
Car

e2

Car
e3

e4
Exercise
 Suppose three fuses are examined
in sequence and each receive a pass
(P) or fail
(F) rating as a result of this inspection.
1. Construct a tree diagram to
show the outcomes of the experiment.
2. Write down the sample space.
3. Let A denote the event that exactly one fuse
fails inspection. How would A be defined?
4. Let E denote the event that at most one fuse
fails inspection. What is Ē? A and E? A or E?
Probability
 Probability refers to the chance that a particular
event will occur.
 The probability of an event is the proportion of
times the event is expected to occur in repeated
experiments.
 Let A be an event, then P(A) denotes the
probability that A will occur.
Assigning Probabilities
 Classical Method
 Assigning probabilities based on the assumption of
equally likely outcomes.
Number of ways Ai can occur
P(Ai)
Total number of elementary events
=
 Relative Frequency Method
 Assigning probabilities based on experimentation or
historical data.
Number of times Ai occurs
Relative Freq. of Ai
N

=
Assigning probabilities based on the assignor’s

 Subjective
judgment.Method
Exercises
1. A quiz contains multiple-choice questions
with five possible answers, only one of which
is correct. A student plans to guess the
answers because he knows absolutely
nothing about the subject.
a) Produce the sample space for each question
b) Assign probabilities to the simple
events in the sample space you
produced.
c) Which approach did you use to answer part b.
d) Interpret the probabilities you
assigned in part b.
Exercise
2. The manager of a computer store has kept track
of the number of computers sold per day. On
the basis of this information, the manager
produced the following list of the number of
daily sales: Number of Probability

a) Which approach did the manager Computers

Sold
use to assign the probabilities. 0 .08

b) What is the probability of selling 1

2
.17
.26
2, 3 or 4 computers? 3 .21
4 .18
c) What is the probability of selling 5 .10

6 computers?
Rules of Probability
Rules for
Possible Values
and Sum

Individual Values Sum of All Values

k
0 ≤ P(Ai) ≤ 1
For any event Ai  P(A )  1i
where: i1
k = Number of elementary events
in the sample space
Ai = ith elementary event 12
Complement Rule
 The complement of an event A is the
collection of all possible elementary events
not contained in event A. The complement of
event E is represented by Ā.

A
 Complement Rule:

P(A)  1  Ā
P(A)
Or P(A)  P(A)
, 1
 The Addition Rule
 If A and B are mutually exclusive(if they cannot
occur at the same time), then the probability that
A or B (the union of A and B) will occur is
P(A or B) = P(A) + P(B)-P(Aand B)
where P(Aand B)=0
 General addition Rule for mutually exclusive
events:
 If A1, A2,…, AN are mutually exclusive, then

P(A1  A2 … AN) = P(A1) + P(A2) +…+

P(AN)
 If A and B are not mutually exclusive if some
overlap exists between the two events:
P(A  B) = P(A) + P(B) – P(A  B)
Example: Newspaper Subscribers
 Define events:
 A = event that a randomly selected household
subscribes to the Atlantic Journal
 B = event that a randomly selected household
subscribes to the Beacon News
 Given:
 total number in city, N = 1,000,000
 number subscribing to A, N(A) = 650,000
 P(A)=0.65
 number subscribing to B, N(B) = 500,000
 P(B)=0.50
 number subscribing to both, N(AB) =
250,000
 P(A B)=0.25
Example: Newspaper Subscribers
 What is the probability that a household
subscribes to either newspaper?

P (A  B ) = P (A )+ P (B )  P (A 
B)
 0.65  0.50  0.25  0.90
 What is the probability that a household does not
subscribe to Atlantic Journal?

P (A ) = 1  P (A )
 1  0.65  0.35
Exercises
1) A student is randomly selected from a class
where 35% of the class is left-handed and 50%
are sophomores. We further know that 5% of
the class consists of left-handed sophomores.
What is the probability of selecting:
a) a student that is either left-handed OR a
sophomore?
b) a right-handed sophomore?
c) Are the events of selecting a left-handed student
and selecting a sophomore considered to be
mutually exclusive? Why or why not?
Exercises
2) 42% of the sales force at a large insurance
company have laptop computers, 65% have desk
computers and 24% have both types of computer. A
sales person is selected at random.
a) What is the probability that he/she does not
have a laptop computer?
b) What is the probability that he/she has at
least one of the two types of computer?
Conditional Probability
 The probability of event A occurring, given
that event B has occurred, is called the
conditional probability of event A given event
B, denoted P(A|B):
P(AB)
P(A|B) 
P(B)
where P(B)>0
 Multiplication Rule:
P(A  B)=P(A|B)P(B)
Example: Newspaper Subscribers
 Of the households that subscribe to the Atlantic
Journal, what is the probability that they also
subscribe to the Beacon News?
0.25
P A  B   0.3846
P B | A  0.65
P A
  households
Of the  that subscribe to the Beacon
News, what is the probability that they also
subscribe to the Atlantic Journal?
P A  B 0.25
  0.50
P A | B   P B  0.50

Example
 Of the cars on a used car lot, 70% have air
conditioning (AC) and 40% have a CD player (CD).
20% of the cars have both. What is the probability
that a car has a CD player, given that it has AC ?

CD No CD Total
AC .2 .5 .7
No AC .2 .1 .3
Total .4 .6 1.0

P(CD and AC) .2

P(CD | AC)    .2857
P(AC)
Exercise
 The following table gives the classification of the
amount paid and the method of payment at a
department store.
Credit
Cash Debit Card
Card
Under $20 .09 .03 .04
$20-$100 .05 .21 .18
Over $100 .03 .23 .14
a) What proportion of purchase was paid by debit card?
b) Find the probability that a credit card purchase was
over $100
c) Determine the proportion of purchases made by credit
card or by debit card.
Independent Events
 If A and B are independent events then:
 P(A|B)=P(A) where P(B)>0
 P(B|A)=P(B) where
 P(A  B)=P(A) P(A)>0
P(B)
 In general, if A1, A2, …, Ak are k jointly
independent events then
P(A1  A2  …  Ak)=P(A1) P(A2)
….P(Ak)
Independent vs. Dependent Events
 Independent Events
 Occurrence of one does not influence the
probability of occurrence of the other
E1 = heads on one flip of fair coin
E2 = heads on second flip of same coin

 Dependent Events
 Occurrence of one affects the probability of the
other
E1 = rain forecasted on the news
E2 = take umbrella to work
 Independent Events
Suppose a jar contains 3 red and 4 white marbles. If two marbles are
drawn with replacement, find the following probabilities using a tree
diagram.

a)The probability that both marbles are red.

b)The probability that the first marble is red and the second white.
c)The probability that one marble is red and the other white.
Solution

Let RR be the event that the marble drawn is red, and let W be the event
that the marble drawn is white.

We draw the following tree diagram.

a)The probability that both marbles are red is P(RR)= 3/7 *3/7= 9/49

b)The probability that the first marble is red and the second is white is
P(RW)=3/7*4/7=12/49

c) For the probability that one marble is red and the other is white, we
observe that this can be satisfied if the first is red and the second is white, or
if the first is white and the second is red. The “or” tells us we’ll be using the
Addition Rule from Section 7.2.

Furthermore events RWRW and WRWR are mutually exclusive events, so we

use the form of the Addition Rule that applies to mutually exclusive events.
Therefore

P(one marble is red and the other marble is white)

=P(RW or WR)=P(RW)+P(WR)
=12/49+16/49=28/49
Dependent Events
Suppose a jar contains 3 red and 4 white marbles. If two marbles are drawn without
replacement, find the following probabilities using a tree diagram.

The probability that both marbles are red.

The probability that the first marble is red and the second white.
The probability that one marble is red and the other white.
Solution

Let RR be the event that the marble drawn is red, and let W be the event that the
marble drawn is white.

We draw the following tree diagram.

Example 2

 According to Bank One, 49% U.S. small

of
businesses have Internet Of those
businesses, 35% have their access. web site.
Determine theown
probability that a randomly chosen
small business in US has Internet access and its
own web site.
Let E1 be the event that a small business has
internet access and E2 be the event a small
business has its own web site.
We have P(E1)=0.49 and P(E2|E1)=0.35, so
P(E1  E2)=P(E2|E1)P(E1)=(0.35)(0.49)=0.1715
a)The probability that both marbles are red is P(RR)= 3/7 *2/6=6/42
b)The probability that the first marble is red and the second is white is
P(RW)=3/7*4/6=12/42
For the probability that one marble is red and the other is white, we observe
that this can be satisfied if the first is red and the second is white, or if the
first is white and the second is red. The “or” tells us we’ll be using the
Addition Rule from Section 7.2.
Furthermore events RWRW and WRWR are mutually exclusive events, so we
use the form of the Addition Rule that applies to mutually exclusive events.

Therefore
PP(one marble is red and the other marble is white)
=P(RW or WR)=P(RW)+P(WR)=12/42+12/42=24/42
=P(RW or WR)=P(RW)+P(WR)=12/42+12/42=24/42
Example 3
 About 13% of the population is left-handed. If
two people are randomly selected, what is the
probability both are left-handed? What is the
probability at least one is right-handed?
Let E1 be the event that the first selected person is
a left-handed and E2 be the event that the second
selected person is a left-handed.
We have P(E1)=P(E2)=0.13, so
P(E1E2)=P(E1)P(E2)=(0.13)(0.13)=0.0169
P(At least one is right-handed)=1-
P(E1E2)
=1- 0.0169=0.9831
 Example 1: Newspaper
Subscribers

 Of the Atlantic Journal subscribers, what is

the chance that they also subscribe to the
Beacon News?
 If independent, the P(B|A) = P(A)
 Is P(B|A) = P(A)?
 Know that P(A) = 0.65
 Just calculated that P(B|A) = 0.3846
 0.65 ≠ 0.3846, so P(B|A) ≠ P(A)
 A is not independent of B
 A and B are said to be dependent
Example 4
 The personnel department of an insurance
company has compiled data regarding
promotion, classified by gender. Is
promotion and gender dependent on one
Manager Promoted (E) Not promoted (Ē) Total
another?
Male (A) 46 184 230
Female (Ā) 8 32 40
Total 54 216 270

 Let us check if P(E| If this equality

A)=P(E).
holds, there is no difference in probability of
promotion between a male and a female
manager.
Example 4

Manager Promoted (E) Not promoted (Ē) Total

Male (A) 46 184 230
Female (Ā) 8 32 40
Total 54 216 270

 P(E) = Number of promotions / total number of

managers = 54 /270 = 0.20.
 P(E|A) = Number of promotions | Only male
managers are observed = 46 / 230 = 0.20.
 Conclusion: there is no discrimination in awarding
promotions.
Example-20

A Company produces calculators in three plants with daily

production volumes of 1500, 3000, and 4500 units
respectively. According to past experience, it is known that
the fractions of defective calculators produced by the three
plants are 0.015, 0.020 and 0.022 respectively. If a
calculator is selected from a day's total production and
found to be defective. Find out from which plant the
calculator might have come.
Example
A person has undertaken the construction work. The
probablities are 0.65 that there will be strike, 0.80 that the
construction job will be completed on time if there is a
strike.Determine the probablity that the construction job
will be completed on time.
Example-24

A bolt factory which produces machines A ,B ,C

with 25% , 35% and 40 % respectively . Of their
total output 5 % , 4 % , and 2 % are defective bolts.
A bolt is drawn at random from the product that is
turn to be defective . What is the probablity that it
was manufactured by machine A ?
Exercises

4. purchased two identical

computers. The Reference
Troubleshooting
and Guide suggests that with no
power management features enabled, there is a
70% chance that the operating time will exceed
2.8 hours. Assuming no power management
features are enabled, find the probability that
a) both computers will have an operating time that
exceeds 2.8 hours.
b) at least one of the two computers will have an
operating time that exceeds 2.8 hours.
Exercises

4. purchased two identical

computers. The Reference
Troubleshooting
and Guide suggests that with no
power management features enabled, there is a
70% chance that the operating time will exceed
2.8 hours. Assuming no power management
features are enabled, find the probability that
a) both computers will have an operating time that
exceeds 2.8 hours.
b) at least one of the two computers will have an
operating time that exceeds 2.8 hours.
Counting Principles
 Fundamental Counting Principle
1st principle states that if there are p ways to do one thing,
and q ways to do another thing, then there are p×q ways to
do both things.

Example 1:
Suppose you have 3 shirts (call them A , B , and C ), and 4
pairs of pants (call them w, x, y , and z ). Then you have

3 × 4 = 12 possible outfits:

The counting principle can be extended to situations where

we have more than 2 choices.
For instance-
if there are p ways to do one thing, q ways to a second thing,
and r ways to do a third thing, then there are p×q×r ways to
do all three things.
 Fundamental Counting Principle
2nd principle states that if there are p ways to do one
thing,and q ways to do another thing but both the things
can’t happen together, then there are p+q ways to either of
the two.
Example 2:
Suppose you have 3 shirts (call them A , B , and C ), and 4
pairs of pants (call them w, x, y and z ). Then you have

3 + 4 = 7 way to chose either of the two :

A , B , C or w, x, y, z

The counting principle can be extended to situations where

you have more than 2 choices.
For instance-
if there are p ways to do one thing, q ways to a second
thing, and r ways to do a third thing, then there are p+q+r
 Combinations and Permutations
‘’When the order doesn't matter, it is a Combination’’

My fruit salad is a combination of apples, grapes and

bananas" We don't care what order the fruits are in, they
could also be "bananas, grapes and apples" or "grapes,
apples and bananas", its the same fruit salad.

A Permutation is an ordered Combination.

Permutations
There are basically two types of permutation:
Repetition is Allowed:
Such as the lock above. It could be "333".

No Repetition:
For example -the first three people in a running race. You can't be first and second.
 Permutations
Repetition is Allowed:
When a thing has n different types ... we have n
choices each time!
For example: choosing 3 of those things, the
permutations are:
n×n×n
(n multiplied 3 times)
Which is easier to write down using an exponent of r:
Example: In the bank ATM, there are 10 numbers to choose from (0,1,2,3,4,5,6,7,8,9) and we
choose 4 of them:

10 × 10 ×10×10 = 10^4
= 1,0000 permutations
 Permutations without Repetition
In this case, we have to reduce the number of available
choices each time.

For example -
What order could 16 pool balls be in when it is without
replacement ?
So, our first choice has 16 possibilities, and our next choice has
15 possibilities,then 14, 13, etc.
And the total permutations are: 16 × 15 × 14 × 13 × ... =
20,922,789,888,000
But maybe we don't want to choose them all, just 3 of them, and
that is then:
16 × 15 × 14 = 3,360
But maybe we don't want to choose them all, just 3 of
them, so that is only:
16 × 15 × 14 = 3,360
Without repetition our choices get reduced each time.
But how do we write that mathematically?
So, when we want to select all of the billiard balls the permutations
are:
16! = 20,922,789,888,000
But when we want to select just 3 we don't want to multiply after 14.
How do we do that? There is a neat trick: we divide by 13!
16 × 15 × 14 × 13 × 12 ...13 × 12 ... = 16 × 15 × 14

That was neat. The 13 × 12 × ... etc gets "cancelled out", leaving
only 16 × 15 × 14.

The formula is written:

Example -How many permutations of 3 different digits are there, chosen
from the ten digits 0 to 9 inclusive?(Such as drawing ten numbered
marbles from a bag, without replacement)
Solutions-
The number of permutations of 3 digits chosen from 10 is 10p3
= 10!/(10 - 3)!
= 10 × 9 × 8
= 720

Example-
How many permutations of 4 different letters are there, chosen from the
twenty six letters of the alphabet?
Solutions-
The number of permutations of 4 letters chosen from 26 is 26 p 4
= 26 × 25 × 24 × 23
= 358,800
COMBINATION
A combination is a mathematical technique that determines the
number of possible arrangements in a collection of items where the
order of the selection does not matter. In combinations, you can select
the items in any order.
Example
From a group of 7 men and 6 women, five persons are to be selected to form a
committee so that at least 3 men are there on the committee. In how many ways
can it be done?
Solutions-
We may have (3 men and 2 women) or (4 men and 1 woman) or (5 men only).

Required number of ways = (7C3 x 6C2) + (7C4 x 6C1) + (7C5)

= (525 + 210 + 21)
= 756
A box contains three white balls, four black balls and three red balls. The number
of ways in which three balls can be drawn from the box so that at least one of the
balls is black is-
The required number of ways
(a) 1 black and 2 others = 4C1x 6C2 = 4 × 15 = 60
(b) 2 black and 1 other = 4C2x6C1 = 6 × 6 = 36
(c) All the three black = 4C3 = 4
Total =60 + 36 + 4 = 100
 Chapter 5
Discrete Random Variables
Random Variables: Definitions
 A random variable is a variable that assigns a
numerical value to each outcome of a random
experiment or trial.
 Discrete random variable: Possible values can
be counted or listed
 The number of defective units in a batch of 20
 Number of available computers in a computer lab.
 Continuous random variable: May assume any
numerical value in one or more intervals
 The waiting time for a credit card authorization
 The interest rate charged on a business loan
Discrete Probability Distributions
 The probability distribution of a discrete
random variable is a table, graph or formula
that gives the probability associated with each
possible value that the variable can assume
 Notation: Denote the values of the random
variable by x and the value’s associated
probability by p(x).
 Properties of Discrete Probability Distribution
1. For any value x of the random variable, p(x)  0
2. The probabilities of all the events in the sample
space must sum to 1, that is p(x)=1
 Example 1

Experiment: Toss 2 Coins. Let x = #

heads.outcomes
4 possible
Probability Distribution
T x Value Probability

T 0 1/4 = .25
T H 1 2/4 = .50
2 1/4 = .25
H T
Probability

.50

H .25

H 0 1 x 35

2
Example 2
 Let x be the random variable of the
number of radios sold per week
Number of Radios Sold at Sound City
in a Week

Radios, x Probability , p(x )

0 p(0) = 0.03
1 p(1) =
0.20
2 p(2) =
0.50
3 p(3) =
0.20
4 p(4) =
0.05
5 p(5) =
Example
 What is the chance that two radios will be sold in
a week?
 p(X = 2) = 0.50
 What is the chance that fewer than 2 radios will
be sold in a week?
 p(X < 2) = p(X = 0 or X = 1)
= p(X = 0) + p(X = 1)
= 0.03 + 0.20 = 0.23
 What is the chance that three or more radios will
be sold in a week?
 p(X ≥ 3) = p(X = 3, 4, or 5)
= p(X = 3) + p(X = 4) + p(X = 5)
= 0.20 + 0.05 + 0.02 = 0.27
Exercises
1. Determine whether each of the following is valid
probability distribution.
x 0 1 2 3
p(x) .1 .3 .4 .1

x 5 -6 10 0
p(x) .01 .01 .01 .97

2. Roll two dice and let X be the sum of the two

numbers. Find and graph the
probability distribution of X. Comment on the
distribution.
Mean, Variance and Standard Deviation
 Let X be a discrete random variable with set
of k possible values and probability
distribution p(x):
 The expected value or mean of X is
x =xp(x)
 The variance of X, denoted x is
x =(x- x) 2 p(x)

 The standard deviation of X, denoted x is the

positive square root of the variance.
Example
 The total number of cars to be sold next week is
described by the following probability distribution
x 0 1 2 3 4
p(x) .05 .15 .35 .25 .20

 Determine the expected value and standard

deviation of X, the number of cars sold.
  =0(.05)+1(.15)+2(.35)+3(.25)+4(.20)
x

=2.40
 x =(0-2.4) (.05)+(1-2.4) (.15)+(2-2.4)
2
(.35) 2 2 2

+(3-2.4)2 (.25)+(4-2.4)2(.20)
=1.24
 x=1.11
Exercises
1. A chemical supply company currently has in stock
100 lb of a certain chemical, which it sells to
customers in 5-lb lots. Let X = the number of lots
ordered by a randomly chosen customer, and
suppose that X has probability distribution:
x 1 2 3 4
p(x) 0.2 0.4 0.3 0.1

Compute the mean and the variance of X.

2. An insurance company will insure a $75,000
Hummer for its full value against theft at a premium
of $1500 per year. Suppose that the probability that
the Hummer will be stolen is 0.0075. Calculate the
insurance company's expected net profit.
The Binomial Distribution
 The binomial experiment:
1. Experiment consists of n identical trials
(Bernoulli trials)
2. Each trial results in either “success” or
“failure”
3. Probability of success, p, is constant from trial
to trial (The probability of failure, q, is 1 – p)
4. Trials are independent
 If x is the total number of successes in n
trials of a binomial experiment, then x is a
binomial random variable
Examples
 A manufacturing plant labels items as either
defective or acceptable.
 A firm bidding for a contract will either get the
contract or not.
 A marketing research firm receives survey
responses of “yes I will buy” or “no I will not”.
 New job applicants either accept the offer or
reject it.
 The network works or does not work.
Binomial distribution
 For a binomial random variable x, the
probability of x successes in n trials is given
by the binomial distribution:
n
p (x ) p x n
q for x  0,1,,
(n  !x )!
 x n
 x!
n! is read as “n factorial” and
n! = n × (n-1) × (n-2) × ... × 1
 If x is a binomial random variable with
parameters n and p (so q = 1 – p), then
 The mean x= np
 The variance x2= npq
Binomial Distribution: Applets

How does it look?

Binomial Probabilities
Several Binomial Distributions
Finding probabilities in EXCEL
 If X has Binomial dist with parameters (n, p), then:
 P(X = k) can be obtained from Excel by typing in an
empty cell =binomdist(k, n, p, false) and
returning.
 P(X ≤ k) can be obtained from Excel by typing in an
empty cell =binomdist(k, n, p, true) and returning.
 In MegaStat:
 MegaStat  Probability Discrete Probability
Distributions
 Choose Binomial and enter the values of n
and p
 Click in the Display Graph if the plot of the distribution is
desired.
 Click OK and the output will be given.
Example
 Records show that 30% of the customers in a
shoe store make their payments using a credit
card. This morning 20 customers purchased
shoes.
a) What is the probability that 12 customers used a
credit card?
This is a binomial experiment with n=20 and
p=.30.

20!
P (X  12)  8!12! (0.30)12 (0.70)8  0.0039

In Excel, =BINOMDIST(12,20,0.3,0)
Example
b) What is the probability that at most 7 customers
used a credit card?
20! 20!
P (X  7)  (0.3) (0.7)   
0 20
(0.3) 7
(0.7)13
0! 20! 7!13!
 0.7723
In Excel,
=BINOMDIST(7,20,0
.3,1)

b) What is the expected number of customers who

used a credit card?
x=np=(20)(0.3)=6 customers
Example: MegaStat Output
Exercises
1. A salesperson contacts eight potential
customers per day. From past experience, we
know that the probability of a
potential customer making a purchase is 0.10.
a) What is the probability the salesperson will make
exactly two sales in a day?
b) What is the probability the salesperson will make
at least two sales in a day?
c) What percentage of days will the salesperson not
make a sale?
d) What is the expected number of sales per day?
Exercises
2. Of the customers purchasing laptops, 75%
purchase a Dell model. Let X= the number
among the next 15 purchasers who select
the Dell model.
a) What is the pmf of X?
b) Compute P(X > 10) and P(6  X  10).
c) Compute the mean and the variance of X.
d) If the store currently has in stock 10 Dell
models and 8 Compaq models, what is the
probability that the requests of these 15
customers can all be met from existing stock?
 Chapter 6
Continuous Random Variables
Continuous Probability
Distributions
 A continuous random variable may
assume any numerical value in one or more
intervals
 Use a continuous probability distribution
to assign probabilities to intervals of values
 Examples:
 Age of an employee
 time required to complete a task
 height, in inches

 These can potentially take on any value,

depending only on the ability to measure
accurately.
54
Probability distribution
 The probability distribution of a continuous
random variable is specified by a function, f(x),
such that:
 f(x)  0 for all x
 The total area under the curve of f(x) is equal to
1.
 The function f is called the probability curve of
the probability density function (pdf).
 Distribution Shapes:
 Symmetrical and rectangular (The uniform
distribution)
 Symmetrical and bell-shaped (The normal
 distribution)
Skewed (Skewed either left or right) 55
Area and Probability
 If X is continuous, then
 The blue area under the curve f(x) from x = a to x
= b is the probability that x could take any value in
the range a to b

 P(X = a)= 0 for any number a.

 P(X>a)=1-P(X<a)
 P(a  X  b)=P(a < X < b)=P(X<b)-P(X<a)
Uniform Distribution
 A random variable X is said to be uniformly
distributed over the interval (c, d) if its
density function is
1
f (x ) cx 
 d  d
c and the variance of the
 The expected value
uniform distribution are:

X cd (d  c )
 2  X2  12
2
The Uniform Probability Curve
Example
 The amount of time it takes for a student to
complete a statistics quiz is uniformly
distributed between 30 and 60 minutes.
The pdf is given by
0.035
1

0.030

0.025

1
 for 30  x  60
f x =  30
0.020

Densit
0.015

0
y
otherwise 0.010

0.005

0.000
30 60
X
Example
a) One student is selected at random. Find the
probability that the student requires more
than 55 minutes to complete the quiz.
P(X>55) = (60-55)/(60-30)=0.167
0.035
0.167

0.030

0.025

0.020
Density

0.015

0.010

0.005

0.000
30 55 60
X
Example
b) One student is selected at random. Find the
probability that the student requires 45 to
55 minutes to complete the quiz.
P(45<X<55) = (55-45)/(60-30)=0.3333
0.035
0.333

0.030

0.025

0.020
Density

0.015

0.010

0.005

0.000
30 45 55 60
X
Example
c) Find the expected value and the variance of
the amount of time it takes a student to
complete a statistics quiz.
 The expected value is:
x=(30+60)/2=45
 The variance is:
x =(60-30)
/122
=75 2
Exercise
 The length of time patients must wait to see a
doctor in a local clinic is uniformly distributed
between 15 minutes and 2½ hours.
a) What is the probability of a patient waiting
exactly 50 minutes?
b) What is the probability that a patient would
have to wait between 45 minutes and 2 hours?
c) Compute the probability that a patient would
have to wait over 2 hours.
d) Determine the expected waiting time and its
standard deviation.
The Normal Distribution
 It is the most important continuous distribution:
 Many random variables can be properly
modeled as normally distributed.
 Many distributions can be approximated by a normal
distribution.
 The normal distribution is the cornerstone distribution
of statistical inference.
 A random variable X with mean  and variance  is
normally distributed, abbreviated by N(, ), if its
probability density function is given by
1
f (x) e (1/ 2)[( x  ) x
  /  ]2 
2
Properties of Normal Distribution
 Bell Shaped and Symmetrical
 Mean=Median=Mode
 Spread is determined by σ
 Location is determined by μ
 The total area under the curve is 1.
 It has two tails extending from - to +
 A random variable has a standard normal
distribution provided that it follows N(0, 1).
Many Normal Distributions

 By varying the parameters μ and σ, we obtain

different distributions
 Changing μ shifts the distribution left or right.
 Changing σ increases or decreases the spread.
Empirical Rule: 3 Important
Percentages
 What can we say about the distribution of values
around the mean? There are some general
rules:
 μ ± σ covers about 68.26% of x’s
 μ ± 2σ covers about 95.44% of x’s
 μ ± 3σ covers about 99.74% of x’s
Example
 Ali collected data on the
heights of women ages
18 to 24. He found that
the distribution was
roughly normal, with a
Mean of 64.5 inches
and a standard
deviation of 2.5 inches.
The three percentages
are marked on the
graph.
 Finding Normal Probabilities
 Two facts help calculate normal probabilities:
 The normal distribution is symmetrical.
 Any normal distribution can be transformed into
the “STANDARD NORMAL DISTRIBUTION”.
 Every normal variable with mean  and standard
deviation , can be transformed to
x 
z 

Z is distributed as N(0, 1).
 z measures the number of standard deviations
that x is from the mean 
The Standard
Normal
Finding Normal Probabilities
 To find P(a<x<b) when x is distributed normally:
 Translate x-values to z-values
 Use the Standard Normal Table
The Standard Normal Table
 The standard normal
table is a table that lists
the area under the
standard normal curve
below (to the left of) the
z value of interest, i.e.
P(Z<z).
0.4

0.977

 Example: 0.3

 P(Z < 2.00) = 0.9772 0.2

0.1

0.0
0 2
Z Table example
 Suppose x is normal with mean 8.0 and
standard deviation 5.0. Find P(8 < x <
8.6)
=8 =0
=5 =1

x z
8 0
8.6 0.12

P(8 < x < 8.6) .0478 P(0 < z < 0.12)

Finding Normal Probabilities
 Suppose x is normal with 0.09
8

mean 8.0 and standard 0.08

0.07

deviation 5.0. 0.06

Density
0.05

 Find P(x < 8.6) 0.04

0.03 0.5478

 P(x < 8.6)= P(z < 0.12) 0.02

0.01

= 0.5478 0.00
8.6

0.09

 Find P(x > 10) 0.08

0.07

 P(x > 10) = P(z > 0.0.40) 0.06

0.05

Density
= 1-P(z < 0.40) 0.04

0.03

= 1- 0.6554 0.02 0.345

= 0.3446
0.01

0.00
8 10
Finding probabilities in Excel
 For Standard normal distribution:
 P(Z  a) =normsdist(a)
 For normal distribution with mean  and standard
deviation :
 P(X  a) =normdist(a, , , 1)
 In MegaStat:
 Probability Continuous Probability Distributions
 Choose normal and enter the values of  and 
 Enter the value of x is the “Calculate p given x” window
 Click Preview to see the probability below and above x
or OK to produce the output.
 Note: You can also use Probability Normal distribution
for computations and graphs.
“Backward” Normal Calculations
 We could find the observed value (x) of a given
proportion in N(, 2) by unstandardizing the
z- value.
 State the problem
 Draw a picture
 Use the normal table to find the probability
closest to the one you need and read off the
z- value
 Unstandardize x= + z
Example
Find the z-score that
0
 0.4

corresponds to a cumulative 0.3

area of 0.3632.

Densit
0.2

P(Z<z)=0.3632

y
 z=-0.35
0.1 0.3632

0.0
-0.350 0

 Find the z-score that has 0.4

0

10.75% of the distribution’s

area to its right.
0.3

Density

P(Z>z)=0.1075 0.2

 z=1.24 0.1

0.1075

0.0
0 1.24
Finding quartiles in Excel
 The value of c such that P(Z  c) = , with  known, can be
obtained c=normsinv().
 The value of c such that P(X  c) = , with  known, can be
obtained c=norminv(, , ).
 In MegaStat:
 Probability Continuous Probability Distributions
 Choose normal and enter the values of  and 
 Enter the value of x is the “Calculate x given p” window
 Click Preview to see the desired quartile or OK to
produce the output.
 Note: You can also use Probability Normal distribution
for computations and graphs.
Example
 If X has Normal distribution with =60 and =4, then
 P(X  68) = 0.97725

by typing in EXCEL =normdist(68, 60, 4, 1)

 P( 54 < X < 65) = P( X < 65) – P(X  54)

= 0.8944 – 0.0668 = 0.8276

by typing
=normdist(65,60,4,1)-normdist(54,60,4,1)
 P(X > 68) = 1 – P(X ≤ 68) = 1 – 0.9773 = 0.0227

by typing in EXCEL =1- normdist(68,60,4,1)

 The value of c such that P(X  c) = 0.99 is c = 69.31

by typing in EXCEL =norminv(0.99, 60, 4)

Examples
1) A survey was conducted to measure the number
of hours per week adults spend on home
computers. In the survey, the number of hours
were normally distributed, with a mean of 7
hours and a standard deviation of 1 hour. Find
the probability that the hours spent on the
home computer by the participant are less than
4.5 hours per week.
 P(X<4.5)=P(Z<-2.5)=0.0062
 In Excel, =NORMDIST(4.5, 7, 1, 1)
Examples
2) A person must score in the upper 2% of
the population on an IQ test to qualify for
membership in Mensa, the international
high-IQ society. If IQ scores are
normally distributed with a mean of 100
and a standard deviation of 15, what
score must a person get to qualify for
Mensa?
 P(Z > z) = .02 or P(Z < z) = 1 - .02 = .98
• From the normal table, z = 2.05
• x = +z = 100 + 2.05 (15) = 130.75
 In Excel, =NORMINV(0.98,100,15)
Exercises
1) The average price of personal computers
manufactured by MNM Company is $1,200 with
a standard deviation of $220. Furthermore, it is
known that the computer prices
manufactured by MNM are normally distributed.
a) Computers with prices of more than $1,750
receive a discount. What percentage of the
computers will receive the discount?
b) What are the minimum and the maximum values
of the middle 95% of computer prices?
c) If 513 of the MNM computers were priced at or
below $647.80, how many computers were
produced by MNM?
Exercises
2) The monthly utility bills in Al-Ain are normally
distributed, with a mean of 400 Dhs and a
standard deviation of 50 Dhs.
a) Find the probability that a selected utility
bill is between 300 Dhs and 450 Dhs.
b) What is the 95th percentile of the utility bills?
c) What is the first quartile of the utility bills??
3) A manufacturing process produces items whose
weights are normally distributed. It is known that
22.57% of all the items produced weigh between
100 grams up to the mean and 49.18% weigh
from the mean up to 190 grams. Determine the
mean and the standard deviation.
Exercises
4) In a large section of a statistics class, the points
for the final exam are normally distributed with a
mean of 72 and a standard deviation of 9. Grades
are to be assigned according to the following rule.
 The top 10% receive As
 The next 20% receive Bs
 The middle 40% receive Cs
 The next 20% receive Ds
 The bottom 10% receive Fs
Find the lowest score on the final exam that
would qualify a student for an A, a B, a C, and a
D.