TYPES OF RANDOM VARIABLES

We distinguish between two types of random

DISCRETE RANDOM VARIABLES AND THEIR variables:
PROBABILITY DISTRIBUTIONS
y Discrete random variables
y Continuous random variables

Examples of discrete random

Discrete Random Variable
variables
ariables
y The number of cars sold at a dealership
Definition during a given month
y The number of houses in a certain block
A random variable that assumes finite or y The number of fish caught on a fishing trip
countable values is called a discrete y The number of complaints received at the
random variable. office
ffi off an airline
i li on a given
i d
day
y The number of customers who visit a bank
during any given hour
y The number of heads obtained in three
tosses of a coin

3 4

PROBABLITY DISTRIBUTION OF A Two Characteristics of a

DISCRETE RANDOM VARIABLE Probabilit Distribution
Probability Distrib tion
The probability distribution of a discrete random
Definition variable possesses the following two
characteristics:
The probability distribution of a discrete
random variable lists all the possible values that 1. 0  P (x)  1 for each value of x
the random variable can assume and their
corresponding probabilities. 2. P (x) = 1

5 6
 Example 1: the frequency and relative frequency Example 1: the frequency and relative
distributions of the number of vehicles owned by
y frequency distributions of the number of
families vehicles owned by families (continued)
Number of Relative
Frequency Number of Vehicles Owned Probability
Vehicles Owned Frequency
x P(x)
0 30 /
30/2000 = .015
0 .015
015
1 470 470/2000 = .235
1 .235
2 850 850/2000 = .425
2 .425
425
3 490 490/2000 = .245
3 .245
4 160 160/2000 = .080
4 .080
N = 2000 Sum = 1.000
P(x) = 1.000
Now let x be the number of vehicles owned by a
randomly
d l selected
l t d ffamily.
il W Write
it th
the probability
b bilit
7 distribution of x. 8

Graphical presentation of the

probability distribution from previous Example
p 2: Each of the following g tables lists
certain values of x and their probabilities.
Example
P(x)
0,45 Can you determine whether or not each table
0,4 represents a valid probability distribution?
0,35
0,3
a) x P(x) b) x P(x) c) x P(x)
0,25
0,2
, 0 .08 2 .25 7 .70
0,15 1 .11 3 .34 8 .50
0,1
0,05
2 .39 4 .28 9 -.20
0 3 .27 5 .13
x
0 1 2 3 4

9 10

Answer Key Example 2

a) NO: the respective probabilities DO NOT sum up
to 1, though all are in the range of [0,1]; The following table lists the probability distribution
of the number of breakdowns per week for a
b) YES:
YES both
b th characteristics
h t i ti are satisfied;
ti fi d machine based on past data data.

Breakdowns
0 1 2 3
c)) NO:
NO the
th probability
b bilit off an eventt ((when
h x takes
t k per weekk
value equal to 0.9) cannot be negative, though Probability .15 .20 .35 .30
they
ey sum
su up to o 1.

11 12
 Characteristics: Probability p(x) or f(x) function
and cumulative distribution function F(x) Example 2 (continued)
a)) Present this probability
p y distribution
graphically.

b) Find the probability that the number of

breakdowns for this machine during a given
week is:
i. exactly 2
S
Sum off two
t numbers
b in
i
ii. 0 to 2
tossing two fair dice once iii. more than 1
Number in tossing fair die once iv. at most 1

13 14

Example 2 (continued) Example 2 (continued)

Let x denote the number of breakdowns for this P(x)
machine during a given week; the following table 0,4

lists the probability distribution of x. 0,35

0,3

x P(x) 0,25
a) 0,2
0 .15
0 15
0,15
1 .20 0,1
2 .35 0,05

3 .30 0
x
P(x) = 1.00 0 1 2 3

15 16

Example
p 2 ((concluded)) b))
Example 3
i. P (exactly 2 breakdowns) = P (x = 2) = .35
According to a survey, 60% of all students at a
ii. P (0 to 2 breakdowns) = P (0  x  2) large university suffer from math anxiety. Two
= P (x = 0) + P (x = 1) + P (x = 2) students are randomly selected from this
= .15
15 + .20
20 + .35
35 = .70
70
university. Let x denote the number of
iii. P (more then 1 breakdown) = P (x > 1) students in this sample who suffer from math
= P (x = 2) + P (x = 3) anxiety.
i t Your
Y task
t k is
i to
t develop
d l the
th probability
b bilit
= .35 +.30 = .65 distribution of x.
iv. P (at most one breakdown) = P (x  1)
= P (x = 0) + P (x = 1)
= .15 + .20 = .35

17 18
 Example 3 Continued:
Tree Diagram Example 3 (continued)
Let us define the following two events:

N = the student selected does not suffer from

math anxiety

M = the student selected suffers from math

anxiety
y
P (x = 0) = P(NN) = .16

P (x = 1) = P(NM or MN) = P(NM) + P(MN)

= .24 + .24 = .48
P (x = 2) = P(MM) = .36
36
19 20

MEAN OF A DISCRETE RANDOM

Example 3 (concluded) VARIABLE
Probability distribution of the number of The mean of a discrete variable x is the value that
is expected to occur per repetition
repetition, on average
average, if
students with math anxiety in a sample of two an experiment is repeated a large number of
students is summarized in the following table: times. It is denoted by µ and calculated as

x P(x) μ = x P (x)
0 .16
16 The mean of a discrete random variable x is also
1 .48 called its expected value and is denoted by E (x);
a is,
that s,
2 .36
36 μ = E (x) = x P (x)
P(x) = 1.00

21 22

Example 4: Computing the Mean

Example 4: Computing the Mean (concl ded)
(concluded)
Recall the table from Example 3, where x represents
th number
the b off bbreakdowns
kd ffor a machine
hi d during
i a x P(x))
P( xP(x)
P( )
given week, and P (x) is the probability of the 0 .15 0(.15) = .00
corresponding
p g value of x.
1 .20
20 1( 20) = .20
1(.20) 20
Your task is to find the mean number (or the expected 2 .35 2(.35) = .70
value)) off breakdowns per week for
f this machine. 3 .30 3(.30) = .90
xP(x) = 1.80

Thus the mean is The mean is μ =  x P (x) = 1.80

23 24
 STANDARD DEVIATION OF A Example 5
DISCRETE RANDOM VARIABLE
Baier’s Electronics manufactures computer parts
that are supplied
pp to manyy computer
p companies.
p
The standard deviation of a discrete random Despite the fact that two quality control inspectors
variable x measures the spread of its probability at Baier’s Electronics check every part for defects
distribution and is computed as before it is shipped to another company
company, a few
defective parts do pass through these inspections
undetected. Let x denote the number of defective

¦x
computer parts in a shipment of 400. The
V 2
P ( x)  P 2 following table gives the probability distribution of
x. Compute
C t the
th standard
t d dd deviation
i ti off x.

x 0 1 2 3 4 5
P(x) .02 .20 .30 .30 .10 .08
25 26

Example 5: Computing the

Standard De
Deviation
iation Example 6
x P(x) xP(x) x² x²P(x) Loraine Corporation is planning to market a new
0 .02 .00 0 .00
makeup product
product. According to the analysis made by
the financial department of the company, it will earn
1 .20 .20 1 .20 an annual profit of $4.5 million if this product has high
2 .30 .60 4 1.20 sales and an annual p profit of $ 1.2 million if the sales
3 .30 .90 9 2.70 are mediocre, and it will lose $2.3 million a year if the
4 .10 .40 16 1.60
sales are low. The probabilities of these three
scenarios are .32, .51 and .17 respectively. Thus:
5 .08
08 .40
40 25 2 00
2.00
xP(x) = x²P(x) = a) Let x be the profits (in millions of dollars) earned
2.50 7.70 per annum by the company from this product. Write
th probability
the b bilit di t ib ti off x.
distribution
P ¦ x P x  2 . 50 defective computer parts in 400
 ¦ x P x   P
2 2
7 . 70  ( 2 . 50 ) 2 1 . 45 b)) Calculate the mean and the standard deviation of x.
1 . 204 defective computer parts
27 28

Example 6 (concluded):
Computations to Find the Mean and
Example 6 (continued) Standard Deviation
x P(x) xP(x) x² x²P(x)
a) The following table lists the probability 4.5 .32 1.440 20.25 6.4800
distribution of x 1.2
1 2 .51
51 .612
612 1 44
1.44 0 7344
0.7344
-2.3 .17 -.391 5.29 0.8993
x P(x)
xP(x)
( ) = 1.661  x²P(x)
( ) = 8.1137
4.5 0.32
1.2 0.51
-2.3
23 0 17
0.17
P ¦ xP x  $1.661 million
 ¦ x P x   P
2
8.1137  (1.661)
2 2

$2.314 million
29 30
 FACTORIALS AND COMBINATIONS Factorials

y Factorials Definition
y Combinations The symbol n!, read as “n factorial”, represents the
y Using the Table of Combinations product of all the integers from n to 1. In other words,
n! = n(n - 1)(n – 2)(n – 3). . . 3 . 2 . 1
By definition,
0! = 1

31 32

Example 7 Solution

Evaluate the following: a) 7! = 7 · 6 · 5 · 4 · 3 · 2 · 1 = 5040

a) 7!
b) 10!
c) (12 – 4)!
b) 10! = 10 · 9 · 8 · 7 · 6 · 5 · 4 · 3 · 2 · 1 = 3,628,800
d) (5 – 5)!
c) (12 – 4)! = 8! = 8 · 7 · 6 · 5 · 4 · 3 · 2 · 1 = 40,320

d) (5 – 5)! = 0! = 1

33 34

Combinations Combinations cont.

Definition n denotes the total number of

Combinations give the number of ways x elements
elements can be selected from n elements.
elements The

Cx
notation used to denote the total number of
combinations is = the number of combinations of n
n elements selected x at a time
n Cx
which is read as “the number of combinations of n x denotes the number of elements
elements selected x at a time.” selected p
per selection
35 36
 Combinations (continued) Example 8

An ice cream parlor has six flavors of ice cream.

The number of combinations for selecting x from n distinct Kristen wants to buy two flavors of ice cream. If she
elements is given by the formula randomly selects two flavors
f out off six, how many
combinations are there?

n!
n Cx
x!(n  x)!

37 38

Answer Key Example 9

•n=6 Three members of a jury will be randomly selected

from five people. How many different combinations
•x=2 are possible?
?
6! 6! 6 ˜ 5 ˜ 4 ˜ 3 ˜ 2 ˜1
C2 15
2!(6  2)! 2 ˜1 ˜ 4 ˜ 3 ˜ 2 ˜1
6
2!4!
Thus, there are 15 ways for Kristin to select two ice cream
flavors out of six.

39 40

Example 10: Using the Table of

Solution Combinations

Marv & Sons advertised to hire a financial analyst.

5! 5! 120
C3 10 The company has received applications from 10
3!(5  3)! 3!2! 6 ˜ 2
5 candidates who seem to be equally qualified. The
company manager has decided to call only 3 of
th
these candidates
did t ffor an iinterview.
t i If she
h randomly
d l
selects 3 candidates from the 10, how many total
selections are possible?

41 42
 Example 10: Determining the THE BINOMIAL PROBABILITY
Val e of 10C3
Value DISTRIBUTION
X=3
y The Binomial Experiment
n x 0 1 2 3 … 20 y The Binomial Probability Distribution and binomial
1 1 1 Formula
2 1 2 1 y Using the Table of Binomial Probabilities
3 1 3 3 1 y Probability of Success and the Shape of the Binomial
. . . . . Distribution
. . . . .
… …
n =10 10 1 10 45 120
. . . . .
43 10 C3 44

The Binomial Probability Distribution

and Binomial Form
Formula
la Binomial Distribution
y Number of ‘Successes’ in a of n Observations
For a binomial experiment, the probability of exactly x (T i l )
(Trials)
successes in n trials is given by the binomial formula y # Reds in 15 Spins of Roulette Wheel
y # Defective Items in a Batch of 5 Items
x n x § n · x n x
P( x) n Cx p q ¨¨ ¸¸ p q y # Correct on a 33 Question Exam

© x¹ y # Customers Who Purchase Out of 100 Customers

where Who Enter Store
n = total number of trials y # of Bush-Cheney supporters in survey of 100
p = probability
b bilit off success people
q = 1 – p = probability of failure
x = number of successes in n trials
n-x = number of failures in n trials
45 46

Binomial Distrib
Distribution-How
tion Ho to find it ??? Binomial ???
y 1. Sequence of n Identical Trials y Pick 6 students from this class
y Each flips a coin
y 2.Each Trial Has 2 Outcomes
y Count # of heads
y ‘Success’ (Desired/specified Outcome) or
‘F il ’
‘Failure’ y Pick 6 students from this class
y X= # of 1st year students selected
y 3.Constant Trial Probability
y Random digit g dialing g of 100 numbers
y 4. Trials Are Independent y # of Bush-Cheney supporters
y 5. # of successes in n trials is a binomial y Random digit dialing of 100 numbers
random
d variable
i bl y Sum
S off ages off respondents
d t

47 48
 Example 11 T
Tree diagram
di ffor selecting
l ti th three VCR
VCRs

Five percent of all VCRs manufactured by a large

electronics company are defective. A quality control
inspector randomly selects three VCRsC ffrom the
production line.
What is the probability that exactly one of these three
VCRs are defective?

49 50

Example 11: Answer Key E ample 11

Example 11: Ans
Answer
er Ke
Key (continued)
(contin ed)

Let Therefore,
D = a selected VCR is defective P (1 VCR is defective in 3)
G = a selected VCR is good = P (DGG
( GG or GDG
G G or GGD
GG )
= P (DGG ) + P (GDG ) + P (GGD )
P (DGG ) = P (D )P (G )P (G )
= .0451
0451 + .0451
0451 + .0451
0451
= (.05)(.95)(.95) = .0451
P (GDG ) = P (G )P (D )P (G ) = .1353
= (.95)(.05)(.95)
( 95)( 05)( 95) = .0451
0451
P (GGD ) = P (G )P (G )P (D )
= (.95)(.95)(.05) = .0451

51 52

E ample 11
Example 11: Ans
Answer
er Ke
Key (continued)
(contin ed) E ample 11
Example 11: Ans
Answer
er Ke
Key (concluded)
(concl ded)

n = total number of trials = 3 VCRs y Therefore, the probability of selecting exactly one
defective VCR.
x = number of successes = number of
defective VCRs = 1
n–x=3-1=2 P( x 1) 3 C1 (.
( 05)1 (.
( 95) 2 (3)(.
)( 05)(.
)( 9025) .1354
p = P (success) = .05 y The probability .1354 is slightly different from the
earlier calculation .1353 because of rounding.
g
q = P (failure) = 1 – p = .95
95

53 54
 Example 12 Example 12

At the Express House Delivery Service, providing a) Find the probability that exactly 1 of these 10
high-quality service to customers is the top priority packages will not arrive at its destination within the
off the
th management. t The
Th company guarantees t a specified
f time.
refund of all charges if a package it is delivering b) Find the probability that at most 1 of these 10
does not arrive at its destination byy the specified
p packages will not arrive at its destination within the
time. It is known from past data that despite all specified time.
efforts, 2% of the packages mailed through this
company do not arrive at their destinations within
the specified time. Suppose a corporation mails
10 p packages
g throughg Express
p House Delivery y
Service on a certain day.
55 56

Example 12: Answer Key E ample 12

Example 12: Ans
Answer
er Ke
Key (continued)
(contin ed)

n = total number of packages mailed = 10 a)

x = number of successes = 1
p = P (success) = .02 n – x = number of failures = 10 – 1 = 9
q = P (failure)
(f ) = 1 – .02 = .98
10!
P( x 1) C1 (.02)1 (.98) 9 (.02)1 (.98) 9
1!(10  1)!
10

(10)(.02)(.83374776) .1667

57 58

Example 12: Answer Key

(concl ded)
(concluded) Example 13

b) According to an Allstate Survey, 56% of Baby

Boomers have car loans and are making
P( x d 1) P( x 0)  P( x 1) paymentst on these
th loans
l (USA TODAY
TODAY, O October
t b
28, 2002). Assume that this result holds true for
C 0 (.02) 0 (.98)10  10 C1 (.02)1 (.98) 9
10 the current p
population
p of all Babyy Boomers. Let x
(1)(1)(.81707281)  (10)(.02)(.83374776) denote the number in a random sample of three
.8171  .1667 .9838 Baby Boomers who are making payments on their
loans. Write the probability distribution of x and
car loans
draw a bar graph for this probability distribution.

59 60
 Example 13: Answer Key Example 13: Answer Key

y n = total Baby boomers in the sample = 3 P( x 0) C0 (.56) 0 (0.44) 3 (1)(1)(.085184) .0852

3
y p = P (a
( B Baby
b BBoomer iis making
ki car lloan payments)
t )
= .56 P ( x 1) 3 C1 (.56)1 (.44) 2 (3)(.56)(.1936) .3252
y q = P ((a Baby
B b BBoomer iis not making
ki car lloan
payments) = 1 - .56 = .44 P( x 2) 3 C2 (.56) 2 (.44)1 (3)(.3136)(.44) .4140

P( x 3) 3 C3 (.56) 3 (.44) 0 (1)(.175616)(1) .1756

61 62

Here we have a bar graph of the probability

The following table represents the probability distribution of x.
di t ib ti off x
distribution
P(x)
0,45

x
04
0,4
P (x) 0,35
0,3
0 .0852 0,25
,

1 .3252 0,2
0,15
2 .4140 0,1
0,05
3 .1756 0 x
0 1 2 3

6363 64

Example 14: Using the Table of

Binomial Probabilities Example 14

According to a 2001 study of college students by Using Table IV of Appendix C, answer the following.
a) Find the probability that exactly three college students
Harvard University’s School of Public health, in this sample abstain from drinking
drinking.
19.3% of those included in the study abstained b) Find the probability that at most two college students
from drinking (USA TODAY, April 3, 2002). in this sample abstain from drinking.
c) Find the probability that at least three college students
S
Suppose that
th t off allll currentt college
ll students
t d t ini th
the in this sample abstain from drinking.
United States, 20% abstain from drinking. A d) Find the probability that one to three college students
random sample of six college students is p abstain from drinking.
in this sample g
e) Let x be the number of college students in this sample
selected. who abstain from drinking. Write the probability
distribution of x and draw a bar graph for this
probability distribution.
65 66
 Determining P (x = 3) for n = 6 and p = .20 Example 14: Answers
p =.20
p a) P (x = 3) = .0819
n x .05 .10 .20 … .95 b) P (at most 2) = P (0 or 1 or 2)
n=6 6 0 .7351 .5314 .2621 … .0000
= P (x = 0) + P (x = 1) + P (x = 2)
1 .2321 .3543 .3932 … .0000
= .2621 + .3932 + .2458 = .9011
2 .0305
0305 .0984
0984 .2458
2458 … .0001
0001 c) P ((at least 3)) = P(3( or 4 or 5 or 6))
x=3 3 .0021 .0146 .0819 … .0021
= P (x = 3) + P (x = 4) + P (x =5) + P (x = 6)
4 .0001 .0012 .0154 … .0305
= .0819 + .0154 + .0015 + .0001
= .0989
5 0000
.0000 0001
.0001 0015
.0015 … 2321
.2321
6 .0000 .0000 .0001 … .7351
d) P (1 to 3) = P (x = 1) + P (x = 2) + P (x = 3)
= .3932 + .2458 + .0819 = .7209
P (x = 3) = .0819
67 68

Bar graph for the probability distribution of x.

Probability Distribution of x for n = 6 and p= .20

P(x)
x P(x) 0,45
0 .2621 0,4

1 .3932 0,35
0,3
2 .2458
2458
0,25
3 .0819
0,2
4 .0154 0,15
5 .0015 0,1
6 .0001 0,05
0 x
0 1 2 3 4 5 6

69 70

Probability
y of Success and the Shape
p Bar graph from the probability distribution from
previous table.
of the Binomial Distribution

1. The binomial probability distribution is P(x)

symmetric if p = .50 0,4

Probability Distribution of x for x P(x) 0,3

n = 4 and p = .50
0 .0625
0625
0,2
1 .2500
2 .3750
3750 01
0,1
3 .2500
0
4 .0625
0625 x
0 1 2 3 4
71 72
 Probability
y of Success and the Shape
p Bar graph for the probability distribution for the
previous table
of the Binomial Distribution cont.

2. The binomial probability distribution is skewed P(x)

to the right if p is less than .50. 0,5
Probability Distribution of x for
n = 4 and p = .30
x P(x) 0,4

03
0,3
0 .2401
1 .4116 0,2

2 .2646 0,1

3 .0756 0
x
4 .0081 0 1 2 3 4

73 74

Probability
y of Success and the Shape
p Bar graph for the probability distribution
f
from previous
i table
t bl
of the Binomial Distribution cont.
P(x)
3. The binomial probability distribution is skewed 0,5
to the left if p is greater than .50.
04
0,4

0,3
x P(x)
Probability Distribution of x 0 .0016 0,2
for n =4 and p = .80
1 .0256 0,1

2 .1536 0
x
3 .4096 0 1 2 3 4

4 .4096
75 76

Mean and Standard Deviation of the General rules for mean (expected
Binomial Distrib
Distribution
tion values)
al es)
If X and Y are random variables, a and b are constants:
y The mean and standard deviation of a binomial
1) E ( a ) a
distribution are
2) E ( aX ) aE ( X )
P np and V npq E ( aX  b) aE ( X )  b
y where n is the total number of trails, p is the probability 3) E ( X  Y ) E ( X )  E (Y )
of success, and q is the probability of failure. E ( aX  bY ) aE ( X )  bE (Y )
4) E ( XY ) E ( X ) E (Y ) if X and Y are independent
random variables.

77 78
 R les for Variance
Rules Example 15
y If X and Y are random variables, a and b are
constants, the variance V(X), V(Y) have: y In a Martiz poll of adult drivers conducted in July
2002, 45% said that they “often” or “sometimes”
1. V ( a ) 0 eatt or drink
d i k while
hil d
driving
i i (USA TODAY
TODAY, O October
t b
23, 2002). Assume that this result is true for the
2. V ( aX ) a 2V ( X ) current ppopulation
p of all adult drivers. A sample
p of
3. V ( aX  b) a 2V ( X ) 40 adult drivers is selected. Let x be the number
of drivers in this sample who “often” or
4.. V ( aaX  bY
b ) a 2V ( X )  b2V (Y ) if X aandd Y “sometimes”
sometimes eat or drink while driving
driving. Find the
are independent. mean and standard deviation of the probability
distribution of x.
79 80

THE HYPERGEOMETRIC
Example 15: Answer Key PROBABILITY DISTRIBUTION

n = 40 Let
y N = total number of elements in the population
p = .45,
45 and q = .55
55 y r = number of successes in the population
y N – r = number of failures in the population
P np 40(.
( 45) 18 y n = number
b off trials
t i l ((samplel size)
i )
y x = number of successes in n trials
V npq (40)(.
)( 45)(.
)( 55) 3.146 y n – x = number of failures in n trials

81 82

THE HYPERGEOMETRIC
PROBABILITY DISTRIBUTION HYPERGEOMETRIC vs.
vs BINOMIAL

y The probability of x successes in n trials is given by y The hypergeometric distribution is closely related
number
u be ofo ways
ays
number of ways to the binomial distribution.
n – x fail res can be selected
failures
x successes can be selected
from a total of N – r failures y However, for the hypergeometric distribution:
from a total of r successes
in the population y the trials are not independent, and
in the population
r C x N  r Cn  x
P( x) y the
th probability
b bilit off success changes
h ffrom ttrial
i l

N Cn
y to trial.

number of ways
a sample
l off size
i n can beb selected
l t d
from a population of size N
83 84
 Hypergeometric – limit distribution Hypergeometric – limit distribution

y Consider a hypergeometric distribution with n trials and let y Consider a hypergeometric distribution with n trials and let p =
p = (r/n) denote the probability of a success on the first (r/n) denote the probability of a success on the first trial.
trial.
trial y If the
th population
l ti size
i is
i llarge, th
the tterm (N – n)/(N
)/(N – 1)
y If the population size is large, the term (N – n)/(N – 1) approaches 1.
approaches 1
1. y The
eeexpected
pec ed value
a ue a
and
d variance
a a ce ca
can be written
e
y The expected value and variance can be written E(x) = np and Var(x) = np(1 – p). ?? Binomial ??
E(x) = np and Var(x) = np(1 – p). y When the population size is large, a hypergeometric
distribution can be approximated by a binomial
Note that these are the expressions for the expected distribution with n trials and a probability of success
value and variance of a binomial distribution. p = (r/N)
(r/N).
85 86

Example 16 Example 16: Solution

y Brown Manufacturing makes auto parts that are 20! 5!

˜
sold to auto dealers. Last week the company r C x N  r Cn  x C3 5C1 3!(20  3)! 1!(5  1)!
P ( x 3) 20

N Cn 25 C 4
shipped 25 auto parts to a dealer. Later on, it 25!
found out that five of those parts were defective. 4!(25  4)!
B the
By th time
ti th
the company manager contacted
t t d theth (1140)(5)
.4506
dealer, four auto parts from that shipment have 12,650
already been sold
sold. What is the probability that
three of those four parts were good parts and
Thus, the probability that three of the four parts sold are
one was defective? good and one is defective is .4506.
4506
87 88

Example 17 Example 17: Answers

y Dawn Corporation has 12 employees who hold (a)

managerial positions. Of them, seven are female
and five are male. The company is planning to
r C x N  r Cn  x C3 5 C 0 (35)(1)
send 3 of these 12 managers to a conference. If 3 P( x 3) 7
.1591
managers are randomly
d l selected
l t d outt off 12
12, N Cn 12 C3 220
a) Find the probability that all 3 of them are female
b) Find the probability that at most 1 of them is a female
Thus, the probability that all three of managers selected re
e a e iss .1591.
female 59

89 90
 THE POISSON PROBABILITY
Example 17: Answers DISTRIBUTION

(b) y Using the Table of Poisson probabilities

r C x N  r Cn  x C 0 5 C3 (1)(10)
P( x 0) 7
.0455 y Mean and Standard Deviation of the Poisson
N Cn 12 C3 220 Probability Distribution
r C x N  r Cn  x 7 C1 5C 2 (7)(10)
P( x 1) .3182
N Cn 12 C3 220
P( x d 1) P( x 0)  P ( x 1) .0455  .3182 .3637

91 92

THE POISSON PROBABILITY

DISTRIBUTION (continued)
(contin ed) Examples

Conditions to Apply the Poisson Probability 1. The number of accidents that occur on a given
Distribution highway during a one-week period.
2. The number of customers entering a grocery store
y The following three conditions must be satisfied to during a one –hour interval.
apply the Poisson probability distribution. 3. The
Th numberb off television
t l i i sets t sold
ld att a d
department
t t
1. x is a discrete random variable. store during a given week.
2
2. The occurrences are random
random.
3. The occurrences are independent.

93 94

THE POISSON PROBABILITY

DISTRIBUTION (continued)
(contin ed) Poisson distrib
distribution-characteristics
tion characteristics
y Poisson variables is used to count the number of
successes within a specified time or region
region. E
E.g.
g
y Poisson Probability Distribution Formula number of customers arriving at a bank teller in the
next 5 minutes.
y Poisson variables possess the following properties:
y According
A di tto th
the Poisson
P i probability
b bilit di
distribution,
t ib ti y The number of successes occurred in any interval is
the probability of x occurrences in an interval is independent of the number of successes occurred in any
O other interval.
O e x
y The probability that a success will occur in an interval is
P (x) the same for all intervals of equal size and is
x! proportional to the size of the interval.
y The probability that two or more successes will occur in
y where  is the mean number of occurrences in that an interval approaches zero as the interval becomes
interval and the value of e is approximately smaller.
2.71828.
95 96
 Example-using Poisson instead of
Poisson distrib
distribution-link
tion link to binomial binomial
y Poisson variables can be used to approximate y Probability of a defective screw p = 0.01
Binomial variables when: p in binomial is small y Probability
P b bilit off more ththan 2 d
defects
f t iin a llott off 100
(less than 0.05) and n is large (larger than 100), screws?
y Binomial distribution: P = np = (100)(0.01) = 1
then we can use
y Since p <<1, can use Poisson distribution to
P np approximate solution
to approximate binomial distribution.
xj
P
 
2 2
P ( X d 2) F ( 2) ¦ f (x ) ¦ x ! e P 
e 1 10
 11!  12!
1 2

j 0! 0.9197
j 0 j 0 j
P( X ! 2) 1  P( X d 2) 8.03%

97 98

Example 18 Example 18: Solution

y On average, a household receives 9.5 telemarketing

phone calls per week. Using the Poisson distribution
Ox e O (9.5) 6 e 9.5
f
formula, find
f the probability that a randomly selected P( x 6)
household receives exactly six telemarketing phone x! 6!
calls during a given week
week.
(735,091.8906)(. )( 00007485)
720
0.0764

99 100

Example 19 Solution to Example 19

y A washing machine in a laundromat breaks down an (a)

average of three times per month. Using the Poisson (3) 2 e 3 (9)(
)(.04978707)
probability distribution formula,
f find
f the probability that P( x 2) .2240
2! 2
during the next month this machine will have
(b)
a) exactly two breakdowns
b) at most one breakdown (3) 0 e 3 (3)1 e 3
P( x 0)  P( x 1) 
0! 1!
(1)(.04978707) (3)(.04978707)

1 1
101 102 .0498  .1494 .1992
 Example 20 Example 20: Answer Key

Cynthia’s Mail Order Company provides free =8

examination of its products for seven days. If not
completely satisfied
satisfied, a customer can return the x= 6
product within that period and get a full refund.
According to past records of the company, an
average of 2 of every 10 products sold by this
company are returned for a refund. Using the Ox e  O (8) 6 e 8 (262,144)(.00033546)
Poisson probability distribution formula, find the P( x 6) .1221
x! 6! 720
probability that exactly 6 of the 40 products sold
by this company on a given day will be returned
for a refund.

103 104

Example 21: Using the Table of Portion of Table of Poisson Probabilities

Poisson Probabilities f  = 2.0
for 20


x 1.1 1.2 … 2.0  = 2.0
y On average, two new accounts are opened per day at
0 .1353
1353
an Imperial Saving Bank branch. Using the Poisson
1 .2707
table, find the probability that on a given day the 2 .2707
number of new accounts opened at this bank will be 3 .1804
a) exactly 6 4 .0902
y b) at most 3 5 .0361
x=6 6 .0120 P (x = 6)
y c) at least 7
7 .0034
8 0009
.0009
9 .0002
105 106

Mean and Standard Deviation of the

Example 22: Answers P i
Poisson P
Probability
b bilit Distribution
Di t ib ti

P O
a) P (x = 6) = .0120
b) P (at most 3) =P (x = 0) + P (x = 1) + P (x = 2) +
P (x = 3) =.1353 +.2707 +
.2707 + .1804 = .8571
c) P (at least 7) = P (x = 7) + P (x = 8) + P (x = 9)
= .0034 + .0009 + .0002 = .0045 V2 O
V O
107 108
 Example 22: Answers
Example 22 P b bilit Distribution
Probability Di t ib ti off x for
f  = .9
9

y An auto salesperson sells an average of .9 car per

day. Let x be the number of cars sold by this
salesperson on any given day day. Using the Poisson x P (x)
probability distribution table, 0 .4066
a) Write the probability distribution of x.
1 .3659
3659
b) Draw a graph of the probability distribution.
c) Find the mean, variance, and standard deviation. 2 .1647
3 .0494
0494
4 .0111
5 .0020
0020
109 110 6 .0003

Example 22: Answers (continued)

( )
Bar graph for the probability distribution of previous table E ample 22
Example 22: Ans
Answers
ers (concluded)
(concl ded)
P(x)
0,45
0,4

P O
0 35
0,35
0,3 .9 car
0,25
02
0,2
0,15
V2 O .9
0,1
0 05
0,05
0
V O .9 .949 car
x
0 1 2 3 4 5 6

111 112