Discrete Random Variables

6/15/2010
Discrete Random Variables

Outlines
Discrete Random Variable
Probability Distribution
Probability Mass Function
Cumulative Distribution Function
Mean and Variance
Discrete Uniform Distribution
Binomial Distribution
Poisson Distribution
Discrete Random Variable
A discrete random variable is a random variable

with a finite range.
Ex. Number of scratches on a surface, number of
error bit receive.
1
6/15/2010
Probability Distribution
The Probability distribution of a random variable X is a
description of the probabilities associated with the possible
values of X.
Ex. Let X equal to the number of error bits in the next 4 bits
transmitted. X={0,1,2,3,4}. Probabilities for these values are:
P(X=0)=0.6561, P(X=1)=0.2916, P(X=2)=0.0486
P(X=3)=0.0036, P(X=4)=0.0001

Definition
2
6/15/2010

Example: X denote the number of semiconductor wafers that
need to be analyzed until detecting a large contamination (p).
Assume that the probability that a wafer contains a large
contamination is 0.01.
Determine the probability distribution of X.
S={p, ap, aap, aaap,…}
P(X=2)=P(ap)=0.99(0.01)=0.0099
P(X=x)=P(aaa…ap)=0.99x-1(0.01)

Definition
3
6/15/2010

Example: Suppose that a production of 850 parts contains 50
parts that do not conform to the requirements. Two parts are
selected at random, without replacement.
X: the number of nonconfroming parts in the sample.
What is the cumulative distribution function of X? (F(0), F(1),
F(2)).
800 799 800 50
P(X=0)= 850 ⋅ 849 = 0.886 P(X=1)= 2 ⋅ 850 ⋅ 849 = 0.111
P(X=2)= 50 ⋅ 49 = 0.003
850 849
F (0) = P( X ≤ 0) = 0.886
F (1) = P ( X ≤ 1) = 0.886 + 0.111 = 0.997
F (2) = P ( X ≤ 2) = 1
Mean and Variance
4
6/15/2010
Mean and Variance

Example:
Mean and Variance

Example
5
6/15/2010
Discrete Uniform Distribution

Definition
A trial with only two possible outcomes is called
“Bernoulli trial”.
Flipa coin (Head, Tail)
Guess the gender of baby (Male, Female)
...
The trials that constitute the random experiment are

independent.
The probability of a success in each trial is constant.
6
6/15/2010
Example: Each sample of water has a 10% chance of
containing a particular organic pollutant.
Assume that the samples are independent with regard to the
presence of the pollutant.
Find the probability that in the next 18 samples, exactly 2
contain the pollutant.
X: the number of samples that contain the pollutant in the next
18 samples.
18 
P( X = 2) =  (0.1) 2 (0.9)16 = 0.284
2
7
6/15/2010
Determine the probability that at least 4 samples contain the
pollutant. 18
18 
P( X ≥ 4) = ∑  (0.1) x (0.9)18− x
x=4  x 
= 1 − P ( X < 4)
3
18 
= 1 − ∑  (0.1) x (0.9)18− x
x=0  x 
= 1 − [0.150 + 0.3 + 0.284 + 0.168] = 0.098
E ( X ) = 18(0.1) = 1.8 and V ( X ) = 18(0.1)(0.9) = 1.62
Ex. An automated egg carton loader has a 1% probability of
cracking an egg, and a customer will complain if more than
one egg per dozen is cracked. Assume each egg load is an
independent event.
(a) What is the distribution of cracked eggs per dozen? Include
parameter values.
(b) What is the prob. That a carton of a dozen eggs results in a
complaint?
(c) What is the mean and sd. of the number of cracked eggs in
a carton of one dozen?
8
6/15/2010
Geometric Distributions
Similar to Binomial Distribution: Bernoulli trials with
constant prob. P
No fixed number of trials. Trials are conducted until
a success is obtained.
Geometric Distributions
Example: The probability that a wafer contains a large
particle of contamination is 0.01.
If it is assumed that the wafers are independent, what is the
probability that exactly 125 wafers need to be analyzed
before a large particle is detected?
X: the number of samples analyzed until a large particle is
detected.
P ( X = 125) = (0.99)124 0.01 = 0.0029
9
6/15/2010
Negative Binomial Distribution

The random variable is the number of Bernoulli
trials required to obtained r success results.

Example: suppose the probability that a bit transmitted
through a channel is received in error is 0.1.
Assume the transmissions are independent events
Determine the probability that the 4th errors occur in the10th
trial.
X: the number of bits transmitted until the fourth error.
9
P ( X = 10) =  (0.1) 3 (0.9) 6 (0.1)
 3
10
6/15/2010

Example. A computer system uses passwords constructed from the 26 letters (a-z) or
10 integers (0-9). Suppose there are 10,000 users on the system with unique
passwords. A hacker randomly selects (with replacement) passwords from the
potential set.
(a) There are 9900 users with unique six-character password on the system and the
hacker randomly selects six-character passwords. What is the mean and sd. of the
number of attempts before the hacker selects a user password?
(b) Suppose there are 100 users with unique three-character passwords on the
system and the hacker randomly selects three-character passwords. What is the
mean and sd. Of the number of attempts before the hacker selects a user
password?
Comment on the security differences between six- and three- character passwords?
Hypergeometric Distribution
11
6/15/2010
Ex. A batch of parts contains 100 parts from a local supplier of tubing and
200 parts from outside supplier. If 4 parts are selected randomly without
replacement, what is the probability that they are all from the local
supplier?
Let X equal the number of parts in the sample from the local supplier.
Hypergeometric VS Binomial
12
6/15/2010
Let X denote the random variable that counts the
number of flaws in a length of L mm. The average
number of flaws in L mm. is λ
L mm.
n subintervals
• The Distribution of X can approximated as

Binomial Distribution: E(X)=np=λ, p=λ/n
• Hence:
Flaw <=1,
with prob. =p
•If n →∞,
The probability of a number of events occurring in a fixed
interval if these events occur with a known average rate and
independently of the intervals.
13
6/15/2010
Example: For the case of the thin copper wire, suppose that the
number of flaws follows a Poisson distribution with a mean of
2.3 flaws per millimeter.
Determine the probability of exactly 2 flaws in 1 millimeter of
wire. −2.3 2
e 2.3
λ = 2.3, P ( X = 2) = = 0.265
2!
Determine the probability of 10 flaws in 5 mm of wire.
λ = 5 mm × 2.3 flaws/mm = 11.5 flaws,
11.510
P(X = 10 ) = e −11.5 = 0.113
10!
Ex. Message arrive to a computer server according to a
Poisson distribution with a mean rate of 10 per hour. Determine
the length of an interval of time such that the probability that
no message arrive during this interval is 0.90.
14
6/15/2010
Homework
1. Heart failure is due to either natural occurrences (87%) or out side factor (13%). Outside factors
are related to induced substances or foreign objects. Natural occurrences are caused by arterial
blockage, disease, and infection. Suppose that 20 patients will visit an emergency room with heart
failure. Assume that causes of heart failure between individuals are independent.
(a) What is the probability that three individuals have conditions caused by outside factors?
(b) What is the probability that three or more individuals have conditions caused by outside factors?
(c) What is the mean and sd. Of the number of individuals with conditions caused by outside factors?
2. A trading company has eight computers that it uses to trade on the New York Stock Exchange
(NYSE). The probability of a computer failing in a day is 0.005 and the computer fail
independently. Computers are repaired in the evening and each day is an independent trial.
(a) What is the probability that all eight computers fail in a day?
(b) What is the mean number of a days until a specific computer fails?
(c) What is the mean number of a days until all eight computer fails in the same day?
Homework
3.The number of flaws in bolts of cloth in textile manufacturing is assumed to be Poisson distributed
with a mean of 0.1 flaw per square meter.
(a) What is the probability that there are two flaws in 1 square meter of cloth?
(b) What is the probability that there is one flaw in 10 square meters of cloth?
(c) What is the probability that there is no flaws in 20 square meters of cloth?
(d) What is the probability that there are at least 2 flaws in 10 square meters of cloth?
4. A congested computer network has a 1% chance of losing a data packet and packet losses are
independent events. An email message requires 100 packets.
(a) What is the distribution of data packets that must be resent? Include the parameter values.
(b) What is the probability that two or more packets must be sent?
(c) What is the mean and sd. of the number of packet that must be resent?
(d) If there are 10 messages and each contains 100 packets, what is the probability that at
least one message requires two or more packets be resent?
15

Discrete Random Variables

Uploaded by

Discrete Random Variables

Uploaded by

6/15/2010

Discrete Random Variables

Probability Mass Function

Cumulative Distribution Function

Mean and Variance

Discrete Uniform Distribution

Discrete Random Variable

A discrete random variable is a random variable

Probability Mass Function

Probability Mass Function

Cumulative Distribution Function

Cumulative Distribution Function

Mean and Variance

Mean and Variance

Mean and Variance

Discrete Uniform Distribution

The trials that constitute the random experiment are

= 1 − [0.150 + 0.3 + 0.284 + 0.168] = 0.098

E ( X ) = 18(0.1) = 1.8 and V ( X ) = 18(0.1)(0.9) = 1.62

P ( X = 125) = (0.99)124 0.01 = 0.0029

Negative Binomial Distribution

Negative Binomial Distribution

Negative Binomial Distribution

• The Distribution of X can approximated as

You might also like