Discrete Probability Distributions

Discrete Probability
Distributions
BITS Pilani Dr. Udayan Chanda, Department of Management, BITS Pilani.
Pilani|Dubai|Goa|Hyderabad
Learning Objectives
In this session, you learn:
• The properties of a probability distribution
• To calculate the expected value and variance of a probability

distribution
• To calculate probabilities from binomial, Poisson and

Hypergeometric distributions
• How to use the binomial, Poisson and Hypergeometric

distributions to solve business problems
Discrete Probability Distribution
BITS Pilani, Deemed to be University under Section 3 of UGC Act, 1956
Random Variables
• Random variable - a quantity resulting from
an experiment that, by chance, can assume
different values
16-Aug-17 3
Types of Random Variables
• Discrete Random Variable can assume only
certain clearly separated values. It is usually
the result of counting something
• Continuous Random Variable can assume an

infinite number of values within a given range.
It is usually the result of some type of
measurement
16-Aug-17 4
Definitions
Random Variables
Random
Variables
Discrete Continuous
Random Variable Random Variable

Discrete Random Variables
• Can only assume a countable number of
values
Examples:
– Roll a die twice

Let X be the number of times 4 occurs
(then X could be 0, 1, or 2 times)
– Toss a coin 5 times.
Let X be the number of heads
(then X = 0, 1, 2, 3, 4, or 5)
Probability Distribution For A
Discrete Random Variable
A probability distribution for a discrete random
variable is a mutually exclusive listing of all possible
numerical outcomes for that variable and a probability of
occurrence associated with each outcome
Number of Classes Taken Probability

2 0.2
3 0.4
4 0.24
5 0.16

Example of a Discrete Random
Variable Probability Distribution
Experiment: Toss 2 Coins. Let X = # heads.
4 possible outcomes Probability Distribution

T T X Value Probability
0 1/4 = 0.25
T H 1 2/4 = 0.50
2 1/4 = 0.25
H T
0.50
Probability 0.25
H H
Discrete Probability Distribution 0 1 2 X
Discrete Distributions
Probability Distributions
• A discrete probability distribution assigns a
probability to each value of a discrete random
variable X.
• To be a valid probability, each probability must be
between
0  P(xi)  1
• and the sum of all the probabilities for the values
of X must be equal to unity.
n
 P( x )  1
i 1
i
Example: Coin Flips

When you flip a coin
1st Toss 2nd Toss 3rd Toss
three times, the
sample space has H H H
eight equally likely H H T
simple events..
events H T H
They are
are:: H T T
T H H
T H T
T T H
T T T
If X is the number of heads, then X is a random
variable whose probability distribution is as follows:
Possible Events x P(x)
TTT 0 1/8
HTT, THT, TTH 1 3/8
HHT, HTH, THH 2 3/8
HHH 3 1/8
Total 1
Note that the values
of X need not be
equally likely..
likely 0.40
0.35
However, they must 0.30
Probability
sum to unity
unity..
0.25
0.20
0.15
Note also that a 0.10
discrete probability 0.05

0.00
distribution is 0 1 2 3
Num ber of Heads (X)
defined only at
specific points on
the X-axis
axis..
Expected Value (Measuring Center)
• Expected Value (or mean) of a discrete
random variable (Weighted Average)
N
  E(X)   Xi P( Xi )
i1
– Example: Toss 2 coins, X P(X)
X = # of heads, 0 0.25
1 0.50
compute expected value of X:
2 0.25
E(X) = ((0)(0.25) + (1)(0.50) + (2)(0.25))

= 1.0
Example: Service Calls
The probability distribution of emergency service
calls on Sunday by Ace Appliance Repair is:
x P(x)
What is the average or expected
0 0.05
number of service calls?
1 0.10
2 0.30
3 0.25
4 0.20
5 0.10
Total 1.00
First calculate xiP(xi):

x P(x) xP(x) The sum of the xPxP((x)
0 0.05 0.00 column is the expected
1 0.10 0.10 value or mean of the
2 0.30 0.60 discrete distribution.
3 0.25 0.75 5
4 0.20 0.80 E ( X )     xi P ( xi )
5 0.10 0.50 i 1
Total 1.00 2.75
This particular
0.30
probability distribution
0.25
is not symmetric
0.20
around the mean
Probability
0.15
0.10
 = 2.75.
0.05
However, the mean
0.00
0 1 2 3 4 5 is still the balancing
 = 2.75
Num ber of Service Calls
point.
Because E(X) is an average
average,, it does not have to be an
observable point.
Application: Life Insurance
• Expected value is the basis of life insurance.

• For example, what is the probability that a 30-
30-
year--old white female will die within the next year?
year
• Based on mortality statistics, the probability is
.00059 and the probability of living another year is
1 - .00059 = .99941.
• What premium should a life insurance company
charge to break even on a $500,000 1-
1-year term
policy?
Application: Life Insurance
Let X be the amount paid by the company to settle

the policy.
Event x P(x) xP(x) The total expected
Live 0 .99941 0.00 payout is
Die 500,000 .00059 295.00
Total 1.00000 295.00
Source: Centers for Disease Control and Prevention,
National Vital Statistics Reports, 47, no. 28 (1999).
So, the premium should be $295 plus whatever

return the company needs to cover administrative
overhead and profit.
Application: Raffle Tickets
• Expected value can be applied to raffles and
lotteries.
• If it costs $2 to buy a ticket in a raffle to win a new
car worth $55,000 and 29,346 raffle tickets are
sold, what is the expected value of a raffle ticket?
• If you buy 1 ticket, what is the chance you will

1 29,345
win = lose = 29,346
29,346
Application: Raffle Tickets
• Now, calculate the E(X):

E(X) = (value if you win)P
win)P(win) + (value if you lose)P
lose)P(lose)
= (55,000) 1 + (0) 29,345

29,346 29,346
= (55,000)(.000034076) + (0)(.999965924) = $1.87
• The raffle ticket is actually worth $1.87. Is it worth

spending $2.00 for it?
Measuring Dispersion
• Variance of a discrete random variable
N
σ 2   [Xi  E(X)]2 P(Xi )
i1
• Standard Deviation of a discrete random variable
N
σ  σ2   i
[X
i1
 E(X)]2
P(Xi )
where:
E(X) = Expected value of the discrete random variable X
Xi = the ith outcome of X
P(Xi) = Probability of the ith occurrence of X
Measuring Dispersion (continued)
– Example: Toss 2 coins, X = # heads,

compute standard deviation (recall E(X) = 1)
σ  [X  E(X)] P(X )
i
2
i
σ  (0  1)2 (0.25)  (1 1)2 (0.50)  (2  1)2 (0.25)  0.50  0.707
Possible number of heads

= 0, 1, or 2
16-Aug-17 Discrete Probability Distribution

Mean, Variance, and Standard
Deviation of a Probability Distribution - Example
• John Ragsdale sells new

cars for Pelican Ford. John
usually sells the largest
number of cars on
Saturday. He has
developed the following
probability distribution for
the number of cars he
expects to sell on a
particular Saturday.
16-Aug-17 23
Mean of a Probability Distribution - Example
16-Aug-17 24
Variance and Standard
Deviation of a Probability Distribution - Example
16-Aug-17 25
Probability Distributions
Probability
Distributions
Discrete Continuous
Probability Probability
Distributions Distributions
16-Aug-17
Uniform Distribution
 Characteristics of the Uniform Distribution
• The uniform distribution describes a random

variable with a finite number of integer values
from a to b (the only two parameters)
parameters)..
• Each value of the random variable is equally likely

to occur.
• Consider the following summary of the uniform

distribution:
a = lower limit
Parameters
b = upper limit
1
PMF P( x) 
b  a 1
Range axb
ab
Mean
2
Std. Dev. (b  a)  12  1
12
Used as a benchmark, to generate random
Comments
integers, or to create other distributions.
 Example: Rolling a Die
• The number of dots on the roll of a die form a uniform
random variable with six equally likely integer values:
1, 2, 3, 4, 5, 6
• What is the probability of rolling any of these?
0.18 1.00
0.16 0.90
0.14 0.80
0.70
0.12
Probability
Probability
0.60
0.10
0.50
0.08
0.40
0.06
0.30
0.04 0.20
0.02 0.10
0.00 0.00
1 2 3 4 5 6 1 2 3 4 5 6
Number of Dots Show ing on the Die Number of Dots Show ing on the Die
PMF for one die CDF for one die

 Example: Rolling a Die
1 1 1
• The PMF for all x is: P( x)   
b  a 1 6 11 6
• Calculate the mean as:
a  b 1 6
  3.5
2 2
• Calculate the standard deviation as:
(b  a)  1
2
1

(6  1)  1
2
1
 1.708
12 12
 Application: Pumping Gas
 On a gas pump, the last two digits (pennies) displayed
will be a uniform random integer (assuming the pump
stops automatically).
0.012 1.000
0.900
0.010
0.800
0.700
0.008
0.600
0.006 0.500
0.400
0.004
0.300
0.200
0.002
0.100
0.000 0.000
0 10 20 30 40 50 60 70 80 90 0 10 20 30 40 50 60 70 80 90
Pennies Digits on Pum p Pennies Digits on Pum p
PMF CDF
The parameters are: a = 00 and b = 99
 Application: Pumping Gas
• The PMF for all x is:
1 1 1
P( x)     .010
b  a  1 99  0  1 100
• Calculate the mean as:
a  b 0  99
  49.5
2 2
• Calculate the standard deviation as:
(b  a)  1  1
2

(99  0)  1  1
2
 28.87
12 12
Binomial Probability Distribution
 Observations are independent

 The outcome of one observation does not affect the
outcome of the other
 Two sampling methods deliver independence

 Infinite population without replacement
 Finite population with replacement
16-Aug-17 Discrete Probability Distribution

Possible Applications for the
Binomial Distribution
• A manufacturing plant labels items as either defective or
acceptable
• A firm bidding for contracts will either get a 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

16-Aug-17 BITS Pilani, Deemed to be University under Section 3 of UGC Act, 1956
Bernoulli Distribution
 Bernoulli Experiments
• A random experiment with only 2 outcomes is a
Bernoulli experiment
experiment..
• One outcome is arbitrarily labeled a “success” (denoted

X = 1) and the other a “failure” (denoted X = 0).
p is the P(success), 1 – p is the P(failure).
• “Success” is usually defined as the less likely outcome

so that p < .5 for convenience.
• Note that P(0) + P(1) = (1 – p) + p = 1 and 0 < p < 1.

Consider the following Bernoulli experiments:
Bernoulli Experiment Possible Outcomes Probability of
“Success”
Flip a coin 1 = heads p = .50
0 = tails
Inspect a jet turbine blade 1 = crack found p = .001
0 = no crack found
Purchase a tank of gas 1 = pay by credit card p = .78
0 = do not pay by credit
card
• The expected value (mean) of a Bernoulli experiment is
calculated as:
2
E ( X )   x i P ( xi )  (0)(1  p)  (1)(p)  p
i 1
• The variance of a Bernoulli experiment is calculated as:
2
V ( X )    xi  E ( X )  P( xi )  (0  p) 2 (1  p)  (1  p) 2 (p)  p(1  p)
2
i 1
• The mean and variance are useful in developing the

next model.
 Characteristics of the Binomial Distribution
• The binomial distribution arises when a Bernoulli
experiment is repeated n times.
• Each Bernoulli trial is independent so the
probability of success p remains constant on each
trial.
• In a binomial experiment, we are interested in X =
number of successes in n trials. So,
X = x1 + x2 + ... + xn
• The probability of a particular number of successes P(X)
is determined by parameters n and p.
 Characteristics of the Binomial Distribution
• The mean of a binomial distribution is found by adding the
means for each of the n Bernoulli independent events:
p + p + … + p = np
• The variance of a binomial distribution is found by adding the
variances for each of the n Bernoulli independent events
events::
p(1
(1--p)+ p(1
(1--p) + … + p(1
(1--p) = np(1
(1--p)
• The standard deviation is
np(1
(1--p)
Parameters n = number of trials
p = probability of success
PMF n!
P( x)  p x (1  p)n x
x !(n  x)!
Excel function =BINOMDIST(k,n,p,0)
Range X = 0, 1, 2, . . ., n
Mean np
Std. Dev.
np(1  p)
Comments Skewed right if p < .50, skewed left if
p > .50, and symmetric if p = .50.
Example:
Calculating a Binomial Probability
What is the probability of one success in five
observations if the probability of an event of
interest is .1?
X = 1, n = 5, and π = 0.1
n!
P(X  1)  π X (1  π ) n  X
X!(n  X)!
5!
 (0.1)1 (1  0.1)5 1
1!(5  1)!
 (5)(0.1)(0.9) 4
 0.32805
The Binomial Distribution
Example
Suppose the probability of purchasing a defective computer
is 0.02. What is the probability of purchasing 2 defective
computers in a group of 10?
X = 2, n = 10, and π = .02
n!
P(X  2)  π X (1  π ) n  X
X!(n  X)!
10!
 (.02)2 (1  .02)10 2
2!(10  2)!
 (45)(.0004)(.8508)
 .01531
Example
There are five flights daily from Pittsburgh via US
Airways into the Bradford, Pennsylvania,
Regional Airport. Suppose the probability that
any flight arrives late is .20.
What is the probability that none of the flights

are late today?
16-Aug-17 43
Example (contd..)
• Solution
16-Aug-17 44
Shape
• The shape of the binomial P(X) n = 5 π = 0.1

.6
distribution depends on .4
the values of π and n .2
0
 Here, n = 5 and π = .1 0 1 2 3 4 5 X
P(X) n = 5 π = 0.5
.6
.4
.2
0
 Here, n = 5 and π = .5 0 1 2 3 4 5 X
Using Binomial Tables
n = 10
x … π=.20 π=.25 π=.30 π=.35 π=.40 π=.45 π=.50
0 … 0.1074 0.0563 0.0282 0.0135 0.0060 0.0025 0.0010 10
1 … 0.2684 0.1877 0.1211 0.0725 0.0403 0.0207 0.0098 9
2 … 0.3020 0.2816 0.2335 0.1757 0.1209 0.0763 0.0439 8
3 … 0.2013 0.2503 0.2668 0.2522 0.2150 0.1665 0.1172 7
4 … 0.0881 0.1460 0.2001 0.2377 0.2508 0.2384 0.2051 6
5 … 0.0264 0.0584 0.1029 0.1536 0.2007 0.2340 0.2461 5
6 … 0.0055 0.0162 0.0368 0.0689 0.1115 0.1596 0.2051 4
7 … 0.0008 0.0031 0.0090 0.0212 0.0425 0.0746 0.1172 3
8 … 0.0001 0.0004 0.0014 0.0043 0.0106 0.0229 0.0439 2
9 … 0.0000 0.0000 0.0001 0.0005 0.0016 0.0042 0.0098 1
10 … 0.0000 0.0000 0.0000 0.0000 0.0001 0.0003 0.0010 0
… π=.80 π=.75 π=.70 π=.65 π=.60 π=.55 π=.50 x
Examples:
n = 10, π = .35, x = 3: P(x = 3|n =10, π = .35) = .2522
n = 10, π = .75, x = 2: P(x = 2|n =10, π = .75) = .0004
Binomial Distribution - Table
Five percent of the worm gears produced by an automatic, high-
speed Carter-Bell milling machine are defective. What is the
probability that out of six gears selected at random none will be
defective? Exactly one? Exactly two? Exactly three? Exactly four?
Exactly five? Exactly six out of six?
16-Aug-17
Characteristics
• Mean
μ  E(x)  nπ
 Variance and Standard Deviation
2
σ  nπ (1 - π )
σ  nπ (1 - π )
Where n = sample size
π = probability of the event of interest for any trial
(1 – π) = probability of no event of interest for any trial
Characteristics
Examples
P(X) n = 5 π = 0.1
μ  nπ  (5)(.1)  0.5 .6
.4
.2
σ  nπ (1 - π )  (5)(.1)(1 .1)
0
 0.6708 0 1 2 3 4 5 X
P(X) n = 5 π = 0.5
μ  nπ  (5)(.5)  2.5 .6
.4
σ  nπ (1 - π )  (5)(.5)(1 .5) .2
0
 1.118 0 1 2 3 4 5 X
Characteristics
For the example regarding
the number of late flights,
recall that p =.20 and n =
5.
•What is the average

number of late flights?
•What is the variance of

the number of late flights?
16-Aug-17 50
Binomial Dist. – Mean and Variance:
Another Solution
16-Aug-17 51
Using Excel For The Binomial Distribution

Cumulative Binomial Probability
Distributions
• A study in June 2003 by the Illinois
Department of Transportation concluded that
76.2 percent of front seat occupants used seat
belts. A sample of 12 vehicles is selected.
What is the probability the front seat
occupants in at least 7 of the 12 vehicles are
wearing seat belts?
16-Aug-17 53
Cumulative Binomial Probability
Distributions
• Solution:
16-Aug-17 54
 Example: Quick Oil Change Shop
• It is important to quick oil change shops to ensure
that a car’s service time is not considered “late” by
the customer
customer..
• Service times are defined as either late or not late
late..
• X is the number of cars that are late out of the

total number of cars serviced
serviced..
• Assumptions:
- cars are independent of each other
- probability of a late car is consistent
• What is the probability that exactly 2 of the next n
= 10 cars serviced are late (P
(P(X = 2))?
• P(car is late) = p = .10
• P(car not late) = 1 - p = .90
n!
P( x)  p x (1  p)n x
x !(n  x)!
10!
P(X = 2) = (.1)2(1
(1--.10)10
10--2 = .1937
2!(10--2)!
2!(10
• Alternatively, we could find P(X = 2) using the
=BINOMDIST(k,n,p,0) where
Excel function =BINOMDIST(k,n,p
k = the number of “successes” in n trials
n = the number of independent trials
p = probability of
a “success”
0 means that we
want to calculate
P(X = 2) rather
than P(X < 2)
 Binomial Shape
• A binomial distribution is
skewed right if p < .50,
skewed left if p > .50,
and symmetric if p = .50
• Skewness decreases as n increases, regardless

of the value of p.
• To illustrate, consider the following graphs:

 Binomial Shape
p = .20 p = .50 p = .80

Skewed right Symmetric Skewed left
0.45 0.35 0.45

0.40 0.40
0.30
0.35 0.35
0.30 0.25
0.30
0.25 0.20 0.25
n=5
0.20
0.15 0.20
0.15
0.15
0.10 0.10
0.10
0.05 0.05
0.05
0.00
0.00 0.00
0 5 10 15 20
0 5 10 15 20 0 5 10 15 20
Num ber of Successes
Num ber of Successes Num ber of Successes
 Binomial Shape
p = .20 p = .50 p = .80

0.35 0.30 0.35
0.30 0.30
0.25
0.25 0.25
0.20
0.20 0.20
0.15
0.15 0.15
n = 10 0.10
0.05
0.10
0.05
0.10
0.05
0.00
0.00 0.00
0 5 10 15 20
0 5 10 15 20 0 5 10 15 20
 Binomial Shape
p = .20 p = .50 p = .80

0.25 0.20 0.25

0.18
0.20 0.16 0.20
0.14
0.15 0.12 0.15
0.10
0.10 0.08 0.10
n = 20 0.05
0.06
0.04 0.05
0.02
0.00
0.00 0.00
0 5 10 15 20
0 5 10 15 20 0 5 10 15 20
p = .20 p = .50 p = .80
0.45 0.35 0.45
0.40 0.40
0.30
0.35 0.35
0.25
0.30 0.30
0.25 0.20 0.25
n=5
0.20 0.15 0.20
0.15 0.15
0.10
0.10 0.10
0.05
0.05 0.05
0.00 0.00 0.00
0 5 10 15 20 0 5 10 15 20 0 5 10 15 20
Num ber of Successes Num ber of Successes Num ber of Successes
0.35 0.30 0.35
0.30 0.25 0.30
0.25 0.25
0.20
0.20 0.20
0.15
n = 10 0.15
0.10
0.10
0.05
0.15
0.10
0.05
0.05
0.00 0.00
0.00
0 5 10 15 20 0 5 10 15 20
0 5 10 15 20
0.25 0.20 0.25

0.18
0.20 0.16 0.20
0.14
0.15 0.12 0.15
n = 20
0.10
0.10 0.08 0.10
0.06
0.05
0.04 0.05
0.02
0.00
0.00 0.00
0 5 10 15 20
 Application: Uninsured Patients
• On average, 20% of the emergency room patients at
Greenwood General Hospital lack health insurance.
• In a random sample of 4 patients, what is the probability
that at least 2 will be uninsured?
• X = number of uninsured patients (“success”)
• P(uninsured) = p = 20% or .20
• P(insured) = 1 – p = 1 – .20 = .80
• n = 4 patients
• The range is X = 0, 1, 2, 3, 4 patients.
• What is the mean and standard deviation of this
binomial distribution?
Mean =  = np = (4)(.20) = 0.8 patients
Standard deviation = s = np(1  p)
= 4(.20(1-
4(.20(1-.20)
= 0.8 patients
Here is the binomial distribution for n = 4, p = .20

x PMF CDF
0 .4096 = P(X=0) .4096 = P(X<0)=P(0)

1 .4096 = P(X=1) .8192 = P(X<1)=P(0)+P(1)
2 .1536 = P(X=2) .9728 = P(X<2)=P(0)+P(1)+P(2)
3 .0256 = P(X=3) .9984 = P(X<3)=P(0)+P(1)+P(2)+P(3)
4 .0016 = P(X=4) 1.0000 = P(X<4)=P(0)+P(1)+P(2)+P(3)+P(4)
These probabilities can be calculated using a
calculator or Excel’s function
=BINOMDIST(x,n,p,cumulative
=BINOMDIST( x,n,p,cumulative)) where
cumulative = 0 for a PDF or = 1 for a CDF
PDF formula calculations: PDF Excel formula:
4! = BINOMDIST(0,4,.2,0)
P(0)  (.2)0 (1  .2)40  1 .20  .84
0!(4  0)! =.4096
4! 1 4 1 1 3 = BINOMDIST(1,4,.2,0)
P(1)  (.2) (1  .2)  4  .2  .8
1!(4  1)! =.4096
4! = BINOMDIST(2,4,.2,0)
P(2)  (.2)2 (1  .2)42  4  .22  .82
2!(4  2)! =.1536
4! = BINOMDIST(3,4,.2,0)
P(3)  (.2)3 (1  .2)43  4  .23  .81
3!(4  3)! =.0256
4! = BINOMDIST(4,4,.2,0)
P(4)  (.2)4 (1  .2)44  1 .24  .80
4!(4  4)! =.0016
Binomial probabilities can also be determined by
looking them up in a table for selected values of n
(row) and p (column)
(column)..
p
n X 0.01 0.02 0.05 0.10 0.15 0.20 0.30 0.40 0.50 0.60 0.70 0.80 0.85 0.90 0.95 0.98 0.99
2 0 0.9801 0.9604 0.9025 0.8100 0.7225 0.6400 0.4900 0.3600 0.2500 0.1600 0.0900 0.0400 0.0225 0.0100 0.0025 0.0004 0.0001
1 0.0198 0.0392 0.0950 0.1800 0.2550 0.3200 0.4200 0.4800 0.5000 0.4800 0.4200 0.3200 0.2550 0.1800 0.0950 0.0392 0.0198
2 0.0001 0.0004 0.0025 0.0100 0.0225 0.0400 0.0900 0.1600 0.2500 0.3600 0.4900 0.6400 0.7225 0.8100 0.9025 0.9604 0.9801
3 0 0.9703 0.9412 0.8574 0.7290 0.6141 0.5120 0.3430 0.2160 0.1250 0.0640 0.0270 0.0080 0.0034 0.0010 0.0001 -- --
1 0.0294 0.0576 0.1354 0.2430 0.3251 0.3840 0.4410 0.4320 0.3750 0.2880 0.1890 0.0960 0.0574 0.0270 0.0071 0.0012 0.0003
2 0.0003 0.0012 0.0071 0.0270 0.0574 0.0960 0.1890 0.2880 0.3750 0.4320 0.4410 0.3840 0.3251 0.2430 0.1354 0.0576 0.0294
3 -- -- 0.0001 0.0010 0.0034 0.0080 0.0270 0.0640 0.1250 0.2160 0.3430 0.5120 0.6141 0.7290 0.8574 0.9412 0.9703
4 0 0.9606 0.9224 0.8145 0.6561 0.5220 0.4096 0.2401 0.1296 0.0625 0.0256 0.0081 0.0016 0.0005 0.0001 -- -- --
1 0.0388 0.0753 0.1715 0.2916 0.3685 0.4096 0.4116 0.3456 0.2500 0.1536 0.0756 0.0256 0.0115 0.0036 0.0005 -- --
2 0.0006 0.0023 0.0135 0.0486 0.0975 0.1536 0.2646 0.3456 0.3750 0.3456 0.2646 0.1536 0.0975 0.0486 0.0135 0.0023 0.0006
3 -- -- 0.0005 0.0036 0.0115 0.0256 0.0756 0.1536 0.2500 0.3456 0.4116 0.4096 0.3685 0.2916 0.1715 0.0753 0.0388
4 -- -- -- 0.0001 0.0005 0.0016 0.0081 0.0256 0.0625 0.1296 0.2401 0.4096 0.5220 0.6561 0.8145 0.9224 0.9606
 Compound Events
• Individual probabilities can be added to obtain any

desired event probability.
• For example, the probability that the sample of 4
patients will contain at least 2 uninsured patients
is
• HINT: What inequality means “at least?”
P(X  2) = P(2) + P(3) + P(4)
= .1536 + .0256 + .0016 = .1808
 Compound Events
• What is the probability that fewer than 2 patients
have insurance?
• HINT: What inequality means “fewer than?”
P(X < 2) = P(0) + P(1)
= .4096 + .4096 = .8192
• What is the probability that no more than 2 patients
have insurance?
• HINT: What inequality means “no more than?”
P(X < 2) = P(0) + P(1) + P(2)
= .4096 + .4096 + .1536 = .9728
 Compound Events
It is helpful to sketch a diagram:
"Fewer than two successes."
P (X < 2)
0 1 2 3 4
"At least two successes."

P (X  2)
0 1 2 3 4
"Fewer than two or more than two successes."

P (X < 2 or X > 2)
0 1 2 3 4
 Binomial Probabilities: Excel
• Use Excel’s Insert | Function menu to calculate

the probability of x = 67 successes in n = 1,024
trials with probability p = .048.
• Or use =BINOMDIST(67,1024,0.048,0)
 Recognizing Binomial Applications
• Can you recognize a binomial situation? Look for

n independent Bernoulli trials with constant
probability of success.
In a sample of 20 friends:
• How many are left-
left-handed?
• How many have ever worked on a factory

floor?
• How many own a motorcycle?
Poisson Distribution
 Poisson Processes
• The Poisson distribution was named for French

mathematician Siméon Poisson (1781-
(1781-1840).
• The Poisson distribution describes the number of

occurrences within a randomly chosen unit of time
or space
space..
The Poisson Distribution
Definitions
• You use the Poisson distribution when you are interested in the
number of times an event occurs in a given area of opportunity.
• An area of opportunity is a continuous unit or interval of time,

volume, or such area in which more than one occurrence of an
event can occur.
– The number of scratches in a car’s paint
– The number of mosquito bites on a person
– The number of computer crashes in a day

The Poisson Distribution
• Apply the Poisson Distribution when:
– You wish to count the number of times an event occurs in
a given area of opportunity
– The probability that an event occurs in one area of
opportunity is the same for all areas of opportunity
– The number of events that occur in one area of
opportunity is independent of the number of events that
occur in the other areas of opportunity
– The probability that two or more events occur in an area of
opportunity approaches zero as the area of opportunity
becomes smaller
– The average number of events per unit is  (lambda)
• Called the model of arrivals
arrivals,, most Poisson applications
model arrivals per unit of time
time..
• The events occur randomly and independently over a
continuum of time or space
space::
One Unit One Unit One Unit
of Time of Time of Time

|---| |---| |---|
• • •• •• • •••• • • • •• • • ••• • • •
Flow of Time 
• Each dot (•) is an occurrence of the event of interest.
• Let X = the number of events per unit of time.

• X is a random variable that depends on when the
unit of time is observed.
• For example, we could get X = 3 or X = 1 or
X = 5 events, depending on where the randomly
chosen unit of time happens to fall.
One Unit One Unit One Unit
of Time of Time of Time

|---| |---| |---|
• • •• •• • •••• • • • •• • • ••• • • •
• Arrivals (e.g., customers, defects, accidents) must
be independent of each other.
• Some examples of Poisson models in which
assumptions are sufficiently met are:
• X = number of customers arriving at a bank

ATM in a given minute.
• X = number of file server virus infections at

a data center during a 24-hour period.
• X = number of blemishes per sheet of white
bond paper.
• The Poisson model’s only parameter is  (Greek
letter “lambda”).
 represents the mean number of events per unit
of time or space.
space.
• The unit of time should be short enough that the
( < 20).
mean arrival rate is not large (
• To make  smaller, convert to a smaller time unit
(e.g., convert hours to minutes).
• The Poisson distribution is sometimes called the
model of rare events.
events.
• The number of events that can occur in a given
unit of time is not bounded, therefore X has no
obvious limit.
• However, Poisson probabilities taper off toward

zero as X increases.
Parameters  = mean arrivals per unit of time or space
PDF  x e
P( x) 
x!
Range X = 0, 1, 2, ... (no obvious upper limit)
Mean 
St. Dev.

Comments Always right-skewed, but less so for larger .
x  = 0.1  = 0.5  = 0.8  = 1.6  = 2.0
0 .9048 .6065 .4493 .2019 .1353
Here are
1 .0905 .3033 .3595 .3230 .2707
some
2 .0045 .0758 .1438 .2584 .2707
Poisson
3 .0002 .0126 .0383 .1378 .1804
PMFs..
PMFs
4 -- .0016 .0077 .0551 .0902
5 -- .0002 .0012 .0176 .0361
6 -- -- .0002 .0047 .0120
7 -- -- -- .0011 .0034
8 -- -- -- .0002 .0009
9 -- -- -- -- .0002
Sum 1.0000 1.0000 1.0000 1.0000 1.0000
Poisson distributions are always right-skewed but become
less skewed and more bell-shaped as  increases.
 = 0.8  = 1.6  = 6.4

0.50 0.35 0.18
0.45 0.16
0.30
0.40 0.14
0.35 0.25
0.12
0.30 0.20 0.10
0.25
0.15 0.08
0.20
0.06
0.15 0.10
0.10 0.04
0.05
0.05 0.02
0.00 0.00 0.00
0 4 8 12 16 0 4 8 12 16 0 4 8 12 16
Number of Calls Number of Calls Number of Calls
 Example: Credit Union Customers
 On Thursday morning between 9 A.M. and 10
A.M. customers arrive and enter the queue at the
Oxnard University Credit Union at a mean rate of
1.7 customers per minute.
• Find the PMF
PMF,, mean and standard deviation:
 x e (1.7) x e1.7
PMF = P( x)  
x! x!
Mean =  = 1.7 customers per minute.
Standard deviation = s = 1.7 = 1.304 cust

cust/min
/min
 Example: Credit Union Customers
PMF CDF • Here is the Poisson probability
x P(X = x) P(X  x) distribution for
0 .1827 .1827  = 1.7 customers per minute
1 .3106 .4932 on average.
2 .2640 .7572
3 .1496 .9068 • Note that x represents the
4 .0636 .9704 number of customers.
5 .0216 .9920
6 .0061 .9981 • For example, P(X=4) is the
7 .0015 .9996 probability that there are
8 .0003 .9999 exactly 4 customers in the
9 .0001 1.0000 bank.
 Using the Poisson Formula
Formula: Excel function:
1.70 e1.7
These P(0)   .1827 =POISSON(0,1.7,0)
0!
probabilities 1.71 e1.7
can be P(1)   .3106 =POISSON(1,1.7,0)
1!
calculated 1.72 e1.7
using a P(2)   .2640 =POISSON(2,1.7,0)
2!
calculator or 1.73 e1.7
Excel: P(3)   .1496 =POISSON(3,1.7,0)
3!
1.74 e1.7
P(4)   .0636 =POISSON(4,1.7,0)
4!
 Using the Poisson Formula
Formula: Excel function:
Beyond
1.75 e1.7
X = 9, the P(5)   .0216 =POISSON(5,1.7,0)
5!
probabilities 1.76 e1.7
are below P(6)   .0061
6! =POISSON(6,1.7,0)
.0001 1.77 e1.7
P(7)   .0015
7! =POISSON(7,1.7,0)
1.78 e1.7
P(8)   .0003
8! =POISSON(8,1.7,0)
1.79 e1.7
P(9)   .0001 =POISSON(9,1.7,0)
9!
• Here are the graphs of the distributions:
0.35 1.00
0.90
0.30
0.80
0.25 0.70
Probability
Probability
0.60
0.20
0.50
0.15 0.40
0.10 0.30
0.20
0.05
0.10
0.00 0.00
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9
Num ber of Custom er Arrivals Num ber of Custom er Arrivals
Poisson PMF for  = 1.7 Poisson CDF for  = 1.7
• The most likely event is 1 arrival (P

(P(1)=.3106 or
31.1% chance).
• This will help the credit union schedule tellers.
 Compound Events
• Cumulative probabilities can be evaluated by
summing individual X probabilities.
• What is the probability that two or fewer customers
will arrive in a given minute?
P(X < 2) = P(0) + P(1) + P(2)

= .1827 + .3106 + .2640 = .7573
 Compound Events
• You can also use Excel’s function
=POISSON(2,1.7,1) to obtain this probability.
• What is the probability of at least three customers

(the complimentary event)?
P(X > 3) = 1 - P(X < 2) = 1 - .7573 =.2427

 Poisson Probabilities: Tables

X 1.6 1.7 1.8 1.9 2.0 2.1
0 0.2019 0.1827 0.1653 0.1496 0.1353 0.1225
1 0.3230 0.3106 0.2975 0.2842 0.2707 0.2572
2 0.2584 0.2640 0.2678 0.2700 0.2707 0.2700
3 0.1378 0.1496 0.1607 0.1710 0.1804 0.1890
4 0.0551 0.0636 0.0723 0.0812 0.0902 0.0992
5 0.0176 0.0216 0.0260 0.0309 0.0361 0.0417
6 0.0047 0.0061 0.0078 0.0098 0.0120 0.0146
7 0.0011 0.0015 0.0020 0.0027 0.0034 0.0044
8 0.0002 0.0003 0.0005 0.0006 0.0009 0.0011
9 -- 0.0001 0.0001 0.0001 0.0002 0.0003
10 -- -- -- -- -- 0.0001
11 -- -- -- -- -- --
 Poisson Probabilities: Excel

Excel’s menus for calculating
Poisson probabilities
 Recognizing Poisson Applications
• Can you recognize a Poisson situation?
• Look for arrivals of “rare” independent events with no

obvious upper limit
limit..
• In the last week, how many credit card applications did

you receive by mail?
• In the last week, how many checks did you write?
• In the last week, how many e-mail viruses did your

firewall detect?
 Poisson Approximation to Binomial
• The Poisson distribution may be used to approximate a
binomial by setting  = np.
• This approximation is helpful when n is large and Excel is
not available.
• For example, suppose n = 1,000 women are screened for
a rare type of cancer.
• This cancer has a nationwide incidence of 6 cases per
10,000. What is p? p = 6/10,000 = .0006
• This is a binomial distribution with n = 1,000 and p=.0006.
 Poisson Approximation to Binomial
• Since the binomial formula involves factorials (which are
cumbersome as n increases), use the Poisson distribution as
an approximation:
• Set  = np = (1000)(.0006) = .6
• The Poisson PMF to calculate the probability of x

successes.. For example
successes example::
P(X < 2) = P(0) + P(1) + P(2)
= .5488 + .3293 + .0988 = .9769

Here is a comparison of Binomial probabilities and the

respective Poisson approximations.
Poisson approximation: Actual Binomial probability:
1000!
P(2)  .00062 (1  .0006)10002
P(0) = .60 e-0.6 / 0! = .5488 2!(1000  2)! = .5487
1000!
P(1)  .00061 (1  .0006)10001
P(1) = .61 e-0.6 / 1! = .3293 1!(1000  1)! = .3294
1000!
P(0)  .00060 (1  .0006)10000
P(2) = .62 e-0.6 / 2! = .0988 0!(1000  0)! = .0988
Rule of thumb: the approximation is adequate if n >

20 and p < .05.
Hypergeometric Distribution
 Characteristics of the Hypergeometric Dist.
• The hypergeometric distribution is similar to the
binomial distribution.
• However, unlike the binomial, sampling is without

replacement from a finite population of N items.
• The hypergeometric distribution may be skewed

right or left and is symmetric only if the proportion
of successes in the population is 50%.
Parameters N = number of items in the population
n = sample size
s = number of “successes” in population
 s  N  s 
  
 x n  x 
PMF P( x) 
N
 
n 
Range X = max(0, n-N+s)  x  min(
min(ss, n)
Mean np where p = s/N
N n
St. Dev. np(1  p)
N 1
Comments Similar to binomial, but sampling is without replacement
from a finite population. Can be approximated by binomial
with
p = s/N if n/N < 0.05 (i.e., less than 5% sample).
 Characteristics of the Hypergeometric Dist.
The hypergeometric PMF uses the formula for
combinations:
the number of ways to choose
 s x successes from s successes
 s  N  s    = in the population
    x
x n  x
P( x)     
N the number of ways to choose
   N  s  n–x failures from
n  where  =
 n  x  N-s failures in the population
the number of ways to choose

 N  n items from N items in the
 =
 n  population
 Example: Damaged iPods
• In a shipment of 10 iPods, 2 were damaged and 8

are good.
• The receiving department at BestBuy tests a
sample of 3 iPods at random to see if they are
defective.
• Let the random variable X be the number of
damaged iPods in the sample.
Now describe the problem:
N = 10 (number of iPods in the shipment)
n = 3 (sample size drawn from the shipment)
s = 2 (number of damaged iPods in the
shipment (“successes” in population))
N–s = 8 (number of non-
non-damaged iPods in
the shipment)
x = number of damaged iPods in the sample
(“successes” in sample)
n–x = number of non-
non-damaged iPods in the sample
• This is not a binomial problem because p is not
constant.
• What is the probability of getting a damaged iPod
on the first draw from the sample?
p1 = 2/10
• Now, what is the probability of getting a damaged
iPod on the second draw?
p2 = 1/9 (if the first iPod was damaged) or
= 2/9 (if the first iPod was undamaged)
• What about on the third draw?

p3 = 0/8 or
= 1/8 or
= 2/8
depending on what happened in the first two
draws.
 Using the Hypergeometric Formula
Since there are only 2 damaged iPods in the population,
the only possible values of x are 0, 1, and 2. Here are the
probabilities:
PMF Formula Excel Function
 2  8   2!  8! 
     
0 3  0! 2!  3! 5!   56  7
P(0)      = .4667 =HYPGEOMDIST(0,3,2,10)
10   10!  120 15
   3! 7! 
3   
 28   2!   8! 
     
1 2  1! 1!   2! 6!   56  7
P (1)       = .4667 =HYPGEOMDIST(1,3,2,10)
10   10!  120 15
   3! 7! 
3   
 2  8   2!  8! 
     
2 1  2! 0!  1! 7!   8  1
P(2)      = .0667 =HYPGEOMDIST(2,3,2,10)
10   10!  120 15
   3! 7! 
3   
 Using the Hypergeometric Formula

Since the hypergeometric formula and tables are
tedious and impractical, use Excel’s hypergeometric
function to find probabilities.
Session Summary
• Addressed the probability distribution of a
discrete random variable
• Discussed the Binomial distribution
• Discussed the Poisson distribution
• Discussed the Hypergeometric distribution


Discrete Probability Distributions

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Discrete Probability Distributions

Uploaded by

Copyright:

Available Formats

Discrete Probability

• To calculate the expected value and variance of a probability

• To calculate probabilities from binomial, Poisson and

• How to use the binomial, Poisson and Hypergeometric

• Continuous Random Variable can assume an

Discrete Probability Distribution

– Roll a die twice

Number of Classes Taken Probability

Discrete Probability Distribution

4 possible outcomes Probability Distribution

Example: Coin Flips

However, they must 0.30

discrete probability 0.05

– Example: Toss 2 coins, X P(X)

E(X) = ((0)(0.25) + (1)(0.50) + (2)(0.25))

First calculate xiP(xi):

• Expected value is the basis of life insurance.

Let X be the amount paid by the company to settle

So, the premium should be $295 plus whatever

• If you buy 1 ticket, what is the chance you will

• Now, calculate the E(X):

= (55,000) 1 + (0) 29,345

= (55,000)(.000034076) + (0)(.999965924) = $1.87

• The raffle ticket is actually worth $1.87. Is it worth

• Standard Deviation of a discrete random variable

– Example: Toss 2 coins, X = # heads,

σ  (0  1)2 (0.25)  (1 1)2 (0.50)  (2  1)2 (0.25)  0.50  0.707

Possible number of heads

16-Aug-17 Discrete Probability Distribution

• John Ragsdale sells new

• The uniform distribution describes a random

• Each value of the random variable is equally likely

• Consider the following summary of the uniform

PMF for one die CDF for one die

 Observations are independent

 Two sampling methods deliver independence

 Finite population with replacement

16-Aug-17 Discrete Probability Distribution

• A firm bidding for contracts will either get a contract or not

• A marketing research firm receives survey responses of “yes I

• New job applicants either accept the offer or reject it

Discrete Probability Distribution

• One outcome is arbitrarily labeled a “success” (denoted

• “Success” is usually defined as the less likely outcome

• Note that P(0) + P(1) = (1 – p) + p = 1 and 0 < p < 1.

• The mean and variance are useful in developing the

What is the probability that none of the flights

• The shape of the binomial P(X) n = 5 π = 0.1

•What is the average

•What is the variance of

Discrete Probability Distribution

• X is the number of cars that are late out of the

• Skewness decreases as n increases, regardless

• To illustrate, consider the following graphs:

p = .20 p = .50 p = .80

0.45 0.35 0.45

p = .20 p = .50 p = .80

0.35 0.30 0.35

p = .20 p = .50 p = .80

0.25 0.20 0.25

0.35 0.30 0.35

0.30 0.25 0.30

0.25 0.20 0.25