0% found this document useful (0 votes)
60 views56 pages

Chapter 5 PDF Lecture Notes

The document discusses discrete probability distributions. Some key points: - A discrete random variable can take on only a finite or countably infinite number of possible values. - The probability distribution of a discrete random variable specifies the probability that the random variable equals each possible value. - Examples of discrete distributions include the binomial distribution (number of successes in fixed number of trials) and Bernoulli distribution (binary random variable). - Expected value and variance are discussed for discrete random variables. Properties like expected value of sums and constants multiplied by random variables are covered. The document provides examples of calculating probabilities and expected values for discrete random variables following binomial, Bernoulli, and other common discrete distributions.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
60 views56 pages

Chapter 5 PDF Lecture Notes

The document discusses discrete probability distributions. Some key points: - A discrete random variable can take on only a finite or countably infinite number of possible values. - The probability distribution of a discrete random variable specifies the probability that the random variable equals each possible value. - Examples of discrete distributions include the binomial distribution (number of successes in fixed number of trials) and Bernoulli distribution (binary random variable). - Expected value and variance are discussed for discrete random variables. Properties like expected value of sums and constants multiplied by random variables are covered. The document provides examples of calculating probabilities and expected values for discrete random variables following binomial, Bernoulli, and other common discrete distributions.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 56

Chapter 5 Discrete

Probability Distributions
Random variables and their probability
distributions
• A random variable is a real-valued function whose domain is a sample
space.

• Two types: discrete and continuous.

• A random variable X is said to be discrete if it can take on only a finite


number, or a countably infinite number, of possible values x.
Probability Distribution
• A function p(x) is called a probability distribution of the random
variable X, if

• 1. P(X=x)=p(x) is greater or equal to zero for all values of x.

• 2. σ𝑥 𝑝 𝑥 = 1
Example
• Roll a die.

• X: outcome
x 1 2 3 4 5 6
p(x) 1/6 1/6 1/6 1/6 1/6 1/6
Example
• Flip two coins

• X: number of heads

x 0 1 2

p(x) 1/4 1/2 1/4


The distribution function
• The distribution function F(b) for a random variable X is defined as
𝐹 𝑏 =𝑃 𝑋≤𝑏

• Example: Consider the following probability distribution:

P(0) P(1) P(2)


0.04 0.32 0.64
continue
• The distribution function for this random variable has the form

0 𝑏<0
0.04 0≤𝑏<1
•𝐹 𝑏 =𝑝 𝑋≤𝑏 =
0.36 1≤𝑏<2
1 𝑏≥2
5.1
• Among 10 applicants for an open position , 6 are females and 4 are
males, Suppose three applicants are randomly selected from the
applicant pool for final interviews. Find the probability distribution for
X, the number of female applicants among the final three.
• X: 0,1,2,3
4 6 4
•𝑝 𝑋=0 = 3
10 ;𝑝 𝑋 =1 = 1 2
10 ;
3 3
6 4 6
•𝑝 𝑋=2 = 2 1
10 ;𝑝 𝑋 =3 = 3
10
3 3
5.8
• Daily sales records for a computer manufacturing firm show that it
will sell 0, 1, or 2 mainframe computer systems with probabilities as
listed:

Number of sales 0 1 2
Probability 0.7 0.2 0.1
continue
• Find the probability distribution for X, the number of sales in a two-
day period, assuming that sales are independent from day to day,

• Find the probability that at least one sale is made in the two-day
period
Solution
• X: 0,1,2,3,4.
• P(X=0)=0.7^2
• P(X=1)=0.7x0.2+0.2x0.7
• P(X=2)=0.7x0.1+0.1x0.7+0.2^2
• P(X=3)=0.2x0.1+0.1x0.2
• P(X=4)=0.1^2

• The probability that at least one sale is done is equal to : 1-0.7^2=0.51


using the complement or you can compute it directly by summing
p(1)+p(2)+p(3)+p(4)
• When turned on, each of the two switches in the diagram works
properly with probability 0.9. If a switch is working properly, current
can flow through it when it is turned on. Find the probability
distribution for X, the number of closed paths from A to B, when the
switches are on.

• Find the distribution function.


Solution
• Probability distribution: X: 0,1,2
• P(X=0)=p(0)=0.1^2=0.01
• P(1)=0.1x0.9+0.9x0.1=0.18
• P(2)=0.9^2=0.81
• Distribution function:

0 𝑏<0
0.12 = 0.01 0≤𝑏<1
•𝐹 𝑏 =𝑃 𝑋≤𝑏 =
0.12 + 2𝑥0.1𝑥0.9 = 0.19 1≤𝑏<2
1 𝑏≥2
Expected values of random variables
• The expected value of a random variable X having probability
distribution p(x) is given by: 𝜇 = 𝐸 𝑋 = σ𝑥 𝑥𝑝 𝑥 .

• The variance of a random variable X with expected value 𝜇 is given by


𝜎 2 = 𝑉 𝑋 = 𝐸 𝑋 − 𝜇 2 = 𝐸 𝑋 2 − 𝜇2 where 𝐸 𝑋 2 = σ𝑥 𝑥 2 𝑝 𝑥

• The standard deviation is given by 𝜎.


Properties
• For any random variable X and constants a and b

• 𝐸 𝑎𝑋 + 𝑏 = 𝑎𝐸 𝑋 + 𝑏
• 𝐸 𝑎𝑋 + 𝑏 = σ 𝑎𝑥 + 𝑏 𝑝 𝑥 = 𝑎 σ 𝑥𝑝 𝑥 + 𝑏 σ 𝑝 𝑥 = 𝑎𝐸 𝑋 + 𝑏
• 𝑉 𝑎𝑋 + 𝑏 = 𝑎2 𝑉 𝑋
Example
• The manager of a stockroom in a factory knows from her study of
records that X, the daily demand for a certain tool, has the following
probability distribution:
• Find the expected daily demand for the tool and the variance.
• Suppose it costs the factory $100 each time the tool is used. Find the
mean and variance of the daily costs for use of this tool.
Demand 0 1 2
Probability 0.1 0.5 0.4
Solution
• 𝐸 𝑋 = 𝜇 = σ 𝑥𝑝 𝑥 = 0 ∙ 0.1 + 1 ∙ 0.5 + 2 ∙ 0.4 = 1.3

• 𝑉 𝑋 = σ 𝑥 − 𝜇 2 𝑝 𝑥 = 0 − 1.3 2 ∙ 0.1 + 1 − 1.3 2 ∙ 0.5 +


2 − 1.3 2 ∙ 0.4 = 0.41.

• Y: cost; Y=100X
• E(Y)=100E(X)
• V(Y)=100^2V(X)
Tchebysheff’s inequality
• Let X be a random variable with mean 𝜇 and standard deviation 𝜎.
Then for any 𝑘 > 1, we have:
1
• 𝑝 𝑋 − 𝜇 < 𝑘𝜎 ≥ 1 − .
𝑘2

1
• Equivalent to 𝑝 −𝑘𝜎 < 𝑋 − 𝜇 < 𝑘𝜎 ≥ 1 − or
𝑘2
1
• 𝑝 𝜇 − 𝑘𝜎 < 𝑋 < 𝜇 + 𝑘𝜎 ≥ 1 −
𝑘2

1
• At least (1 − )% of the data falls in the interval 𝜇 − 𝑘𝜎, 𝜇 + 𝑘𝜎 .
𝑘2
Example
• The daily production of electric motors at a certain factory averaged
120 with standard deviation of 10. What fraction of days will have a
production level between 100 and 140?

• 𝜇 − 𝑘𝜎 = 100, hence k=2.

1
• Hence 1 − = 3/4.
𝑘2

• At least 75% of the days will have total production in this interval.
17
• The number of breakdowns for a university computer system is
closely monitored by the director of the computing center, because it
is critical to the efficient operation of the center. The number
averages 4 per week, with a standard deviation of 0.8 per week.
• A) Find an interval that must include at least 90% of the weekly
figures on number of breakdowns.

• B) The center director promises that the number of breakdowns will


rarely exceed 8 in a one-week period. Is the director safe in making
this claim?
Solution
1
• 1− = 0.9 → 𝑘 = 3.16
𝑘2

• Interval: 𝜇 − 𝑘𝜎, 𝜇 + 𝑘𝜎

• 𝜇 = 4, 𝜎 = 0.8; 1.47,6.53

• Safe. Because 8 is not in the interval


The Bernoulli distribution
• X is a binary discrete random variable: it has only two outcomes.

• Denote the outcomes by 0 and 1, with p(X=1)=p and p(X=0)=1-p.

• The mean or expected value is equal to: 𝜇 =E(X)= 0p(0)+1p(1)=p


• 𝐸 𝑋 2 = 02 𝑝 0 + 12 𝑝 1 = 𝑝
• The variance is: 𝑉 𝑋 = 𝐸 𝑋 2 − 𝜇2 = 𝑝 − 𝑝2 = 𝑝 1 − 𝑝

• The Bernoulli distribution is a building block in forming other probability


distributions.
The Binomial Distribution
• A random variable Y possesses a binomial distribution if
• The experiment consists of a fixed number of trials
• Each trial can result in one of only two possible outcomes, called
“success” and “failure”
• The probability of success p is constant from trial to trial.
• The trials are independent
• Y is defined as the number of successes among the n trials
• The probability distribution is given by the following formula.

𝑛
•𝑝 𝑦 =𝑝 𝑌=𝑦 = 𝑦
𝑝𝑦 1 − 𝑝 𝑛−𝑦 , 𝑦 = 0,1, ⋯ , 𝑛

• 𝐸 𝑌 = 𝑛𝑝

• 𝑉 𝑌 = 𝑛𝑝 1 − 𝑝
Example
• In a study of lifetimes for a certain type of battery, it was found that
the probability of a lifetime X exceeding 4 hours is 0.135. If three such
batteries are in use in independently operating systems, find the
probability that
• A) Only one of the batteries lasts 4 hours or more.
• B) At least one battery lasts 4 hours or more
Solution
• Y: number of batteries (out of three) lasting 4 hours or more. Clearly Y
has a binomial distribution with n=3 and p=0.135

3
•𝑝 𝑌=1 = 1
0.1351 ∙ 0.8652 = 0.303

• 𝑝 𝑌 ≥ 1 = 1 − 𝑝 𝑌 = 0 = 1 − 0.8653

• 𝑝 𝑌 ≥ 1 = 𝑝 1 + 𝑝 2 + 𝑝(3)
Nb 26, p. 239
• Among persons donating blood to a clinic, 80% are 𝑅𝐻 ÷ (that is, have
the Rhesus factor present in their blood). Five people donate blood at
the clinic on a particular day.
• A) Find the probability that at least one of the five does not have the
Rh factor. 1 − 0.85

• B) Find the probability that at most four of the five have 𝑅𝐻 ÷ .


1 − 0.85
31
• A missile protection system consists of n radar sets operating
independently each with probability 0.9 of detecting an aircraft entering a
specified zone. (All radar sets cover the same zone). If an airplane enters
the zone, find the probability that it will be detected if
• A) n=2;
• 1 − 0.12 = 0.99
• 𝑝 1 + 𝑝 2 = 21 0.9 × 0.1 + 2
2
0.92 = 0.99
• B) n=4; 1 − 0.14
4 4
• 𝑝 1 +𝑝 2 +𝑝 3 +𝑝 4 = 1
0.9 × 0.13 + 2
0.92 × 0.12 +
4 4
• 3
0.93 × 0.1 + 4
0.94
32
• Refer to the previous exercise. How large must n be if it is desired to
have probability 0.99 of detecting an aircraft entering the zone?

• 1 − 0.1𝑛 = 0.99 → 0.1𝑛 = 1 − 0.99 = 0.01 → 𝑛 = 2


35
• A firm sells four items randomly selected from a large lot known to
contain 10% defectives. Let Y denote the number of defectives among
the four sold. The purchaser of the item will return the defective for
repair, and the repair cost is given by 𝐶 = 3𝑌 2 + 𝑌 + 2 . Find the
expected repair cost.
Solution
• 𝐸 𝐶 = 𝐸 3𝑌 2 + 𝑌 + 2 = 3𝐸 𝑌 2 + 𝐸 𝑌 + 2

• Y: Binomial distribution with parameters: n=4, p=0.1

• 𝜇 =E(Y)=np; 𝐸 𝑌 2 =?
• V(Y)=np(1-p)

• 𝑉 𝑌 = 𝐸 𝑌 2 − 𝜇2 → 𝐸 𝑌 2 = 𝑉 𝑌 + 𝜇2 = 𝑛𝑝 1 − 𝑝 + 𝑛𝑝 2
24
• In testing the lethal concentration of a chemical found in polluted
water, it is found that a certain concentration will kill 20% of the fish
that are subjected to it for 24 hours. If 20 fish are placed in a tank
containing this concentration of chemical, find the probability that
after 24 hours.
• A) Exactly 14 survive (0.196-0.087)
• B) At least 10 survive (1-0.001)
• C) At most 16 survive (0.589)
Geometric distribution
• Each trial can result in one of only two possible outcomes, called
“success” and “failure”

• The probability of success p is constant from trial to trial.

• The trials are independent

• Y: the number of the trial on which the first success occurs


• Y has a geometric distribution

• 𝑝 𝑦 =𝑝 1−𝑝 𝑦−1 , 𝑦 = 1,2, …

1
•𝐸 𝑌 =
𝑝

1−𝑝
•𝑉 𝑌 =
𝑝2
Example
• A recruiting firm finds that 30% of the applicants for a certain
industrial job have advanced training in computer programming.
Applicants are selected at random from the pool and are interviewed
sequentially. Find the probability that the first applicant having
advanced training is found on the fifth interview.

• 0.74 × 0.3 = 0.072


Nb 38, p. 245
• Let Y denote a random variable having a geometric distribution, with
probability of success on any trial denoted by p.
• A) Find 𝑝 𝑌 ≥ 2 if p=0.1
• B) Find 𝑝 𝑌 > 4|𝑌 > 2 for general p. Compare the result with the
unconditional probability 𝑝 𝑌 > 2 .
Solution
• 𝑝 𝑌 ≥2 =1−𝑝 𝑌 =1 =1−𝑝
1
• Or, 𝑝 𝑌 ≥ 2 = σ∞
𝑖=1 1 − 𝑝 𝑖𝑝 = 𝑝 1 − 𝑝 =1−𝑝
1− 1−𝑝
𝑎
• 𝑎 + 𝑎𝑟 + 𝑎𝑟 2 +⋯= , 𝑟 <1
1−𝑟
1−𝑝 4 𝑝
𝑝 𝑌>4 σ∞
𝑖=4 1−𝑝
𝑖𝑝
1− 1−𝑝 2
• 𝑝 𝑌 > 4|𝑌 > 2 = = σ∞ 𝑖𝑝 = 1−𝑝 2 𝑝
= 1−𝑝
𝑝 𝑌>2 𝑖=2 1−𝑝
1− 1−𝑝
1−𝑝 2 𝑝
•𝑝 𝑌>2 = σ∞
𝑖=2 1−𝑝 𝑖𝑝 = = 1−𝑝 2
1− 1−𝑝
• 𝑝 𝑌 > 4|𝑌 > 2 = 𝑝 𝑌 > 2
• 𝑝 𝑌 > 𝑎 + 𝑏|𝑌 > 𝑎 = 𝑝 𝑌 > 𝑏

• Memoryless property of the geometric distribution.


Negative binomial distribution
• Let Y denote the number on the trial on which the r-th success occurs
in a sequence of independent Bernoulli trials with p denoting the
common probability of success. The random variable Y has a negative
binomial distribution.

𝑦−1
•𝑝 𝑦 = 𝑟−1
𝑝𝑟−1 1 − 𝑝 𝑦−𝑟 𝑝, 𝑦 = 𝑟, 𝑟 + 1, …

𝑟 𝑟 1−𝑝
•𝐸 𝑌 = ; 𝑉 𝑌 =
𝑝 𝑝2
40
• Suppose 10% of the engines manufactured on a certain assembly line
are defective. If engines are randomly selected one at a time and
tested, find the probability that the first non defective engine is found
on the second trial.

• Geometric: 0.1x0.9
41
• Refer to 40). Find the probability that the third non defective engine is
found
• A) On the fifth trial
• B) On or before the fifth trial
solution
• Negative binomial with parameters r=3 and p=0.9
4
• A) P(y=5)= 2
𝑝2 1 − 𝑝 2 𝑝

• B) third trial or fourth trial or fifth trial

3 4
• 𝑝3 + 2
𝑝2 1 − 𝑝 𝑝 + 2
𝑝2 1 − 𝑝 2 𝑝
43
• Refer to 40). Find the mean and variance of the number of the trial on
which
• A) The first non-defective engine is found
• B) The third non-defective engine is found.

• A) Mean=1/p, Variance=(1-p)/p^2; p=0.9

• B) Mean=r/p, Variance=r(1-p)/p^2; p=0.9, r=3


49
• A large lot of tires contains 10% defectives. Four are to be chosen for
placement on a car.
• A) Find the probability that six tires must be selected from the lot to
get four good ones.
• B) Find the expected value and variance of the number of selections
that must be made to get four good tires.
Solution
5
• 3
𝑝3 1 − 𝑝 2 𝑝 = 0.0656; p=0.9

• Mean: r/p=4/0.9

• Variance: r(1-p)/p^2; p=0.9, r=4


The Poisson Distribution
• The Poisson distribution occurs when we count the number of
occurrences of an event over a given time period.

λ𝑦 𝑒 −λ
•𝑝 𝑦 = for 𝑦 = 0,1,2, …
𝑦!

•𝐸 𝑌 =λ

•𝑉 𝑌 =λ
Example
• For a certain manufacturing industry, the number of industrial
accidents averages three per week.
• A) Find the probability that no accident will occur in a given week.
• B) Find the probability that two accidents will occur in a given week.
• C) Find the probability that at most four accidents will occur in a given
week.
• D) Find the probability that two accidents will occur in a given day.
solution
30 𝑒 −3
•𝑝 0 = = 0.05
0!

32 𝑒 −3
•𝑝 2 = = 0.224
2!

• 𝑝 𝑋 ≤ 4 = 𝑝 0 + 𝑝 1 + 𝑝 2 + 𝑝 3 + 𝑝 4 = 0.815

• Number of accidents on 2a given


−0.4286
day: Mean number of accidents per
0.4286 𝑒
day is 3/7. p 2 = =0.06
2!
53
• The number of telephone calls coming into the central switchboard of
an office building averages four per minute.
• A) Find the prob that no calls will arrive in a given 1-minute period.
• B) Find the prob that at least two calls will arrive in a given 1-minute
period.
• C) Find the prob that at least two calls will arrive in a given 2-minute
period.
Solution
40 𝑒 −4
•𝑝 0 = = 0.018
0!

4 0 𝑒 −4 41 𝑒 −4
• 𝑝 𝑋 ≥2 =1−𝑝 0 −𝑝 1 =1 − − =1 − 5𝑒 −4
0! 1!

• 2-minute period: new average is equal to 8.


80 𝑒 −8 81 𝑒 −8
• 𝑝 𝑋 ≥2 =1−𝑝 0 −𝑝 1 =1 − − = 1 − 9𝑒 −8
0! 1!
61
• Customer arrivals at a checkout counter in a department store have a
Poisson with an average of eight per hour. Find the prob that exactly
two customers arrive in the 2-hour period of time
• A) Between 2:00 pm and 4:00 pm.
• B) Between 1:00 pm and 2:00 pm and between 3:00 pm and 4:00 pm
solution
λ2 𝑒 −λ 162 𝑒 −16
• A) 𝑝 2 = =
2! 2!

• B) Same answer as in A) since the intervals 1-2 and 3-4 are


nonoverlapping.
• P(0)p(2)+P(2)P(0)+p(1)p(1)=
66
• A food manufacturer uses an extruder (a machine that produces bite-
size foods such as cookies and many snack foods) that produces
revenue for the firm at the rate of $200 per hour when in operation.
However, the extruder breaks down an average of two times 10 hours
of operation. If Y denotes the number of breakdowns during the time
of operation, the revenue generated by the machine is given by R =
200𝑡 − 50𝑌 2 where t denotes hours of operation. The extruder is
shut down for routine maintenance on a regular schedule and
operates like a new machine after this maintenance. Find the optimal
maintenance interval 𝑡0 to maximize the expected revenue between
shutdowns
Solution
• Y: nb of breakdowns during t hours of operation
• Y: Poisson distribution with λ=2t/10=t/5

2 𝑡 𝑡 2
• 𝐸 𝑅 = 200𝑡 − 50𝐸 𝑌 = 200𝑡 − 50 + =𝑓 𝑡
5 5

190
• 𝑓′ 𝑡 = 0, yields 𝑡0 = = 47.5
4

You might also like