Sie sind auf Seite 1von 22

# QMT 200 NURDIA

## Chapter 5: Special Probability Distributions

5.1 Discrete Distributions
5.1.1 Binomial Distribution

Binomial Experiment
- An experiment which consists of n independent trials, whose outcome of each
trial is either a success with probability p or a failure with probability 1- p.

Definition
The probability density function of a binomial random variable, X having parameters
(n, p) such that X = number of success in the n trials is given by

( ) n x p p C x f
x n x
x
n
,..., 2 , 1 , 0 , 1 ) ( = =

The probability of k successes in n trials is thus,

n k p p C k f k X P
k n k
k
n
,..., 1 , 0 , ) 1 ( ) ( ) ( = = = =

- Notation: ) , ( ~ p n Bin X

- The mean and variance of the binomial random variable, X is given by np x E = ) (
and ) 1 ( ) ( p np x Var = respectively.

QMT 200 NURDIA

Example 1
Four fair coins are tossed. Assume that the outcomes are independent; find the
probability density function of the number of heads obtained.

Solution:

QMT 200 NURDIA

Example 2
The probability that a certain kind of component will survive a shock test is 0.75. Five
components are tested.
a) Find the probability density function of the number of components tested
survives.
b) Calculate the probability that exactly 2 of the next 5 components tested survive.
Solution:

Example 3
Suppose that X is a random variable such that X ~Bin (10, 0.01). Find the mean and
variance of X.
Solution:

QMT 200 NURDIA

5.1.2 Multinomial Distribution

Multinomial Experiment

- An experiment which consists of n independent trials, whose outcome of each
trial is more than 2 possible outcomes.

- In general, if a given trial can result in any one of k possible outcomes E
1
, E
2
,,
E
k
with the probabilities p
1
, p
2
,, p
k
, then the probability density function of the
random variables X
1
, X
2
,, X
k
, representing the number of occurrences E
1
,
E
2
,, E
k
in n independent trials is

k
x
k
x x
k
k
p p p
x x x
n
x x x f ...
,..., ,
) ,..., , (
2 1
2 1
2 1
2 1
|
|
.
|

\
|
=

with n x
k
i
i
=

=1
, and . 1
1
=

=
k
i
i
p

where
|
|
.
|

\
|
k
x x x
n
,..., ,
2 1
=
! 2 1
!..., !
!
x x x
n

Example 4
A human resource worker in a manufacturing company claims that 30% of all workers
own a car, 55% of all workers own a motorcycle and 15% of all workers own a van.
a) Find the probability that of 10 workers randomly chosen, 3 own a car, 5 own a
motorcycle and 2 own a van.
b) What is the probability that of 10 workers randomly chosen, all of them own a
car?
c) What is the probability that of 10 workers randomly chosen, none of them own a
van?

QMT 200 NURDIA

Solution:

QMT 200 NURDIA

5.1.3 Poisson Distribution

Poisson experiment
- An experiment which outcome is the number of times particular events occur in a
given time interval or in a specified region.

- The given time of interval may be of any length such as a minute, an hour, a day
and a week. The specified region could be a line segment, an area, a volume or
a piece of material.

- For example, a random variable X may be defined as:
1. The number of emergency calls per hour received by a hospital.
2. The number of customers that arrive at a supermarket from 10 a.m. to 5 p.m.
3. The number of typing errors per page.
4. The number of bacteria in a given culture.

Definition
A discrete random variable X is said to have a Poisson distribution with parameter , if
its probability density function is given by

!
) ( ) (
x
e
x X P x f
x

= = = where 0 ,..., 2 , 1 , 0 > = n x

- Notation: ) ( ~ P X

- The mean and variance of the Poisson random variable, X is given by = ) (x E
and = ) (x Var respectively.

- Thus, = average number of outcomes in a given time, distance, area or
volume.

QMT 200 NURDIA

Example 5
Suppose that the number of particle that passes through a counter in a millisecond has a
Poisson distribution with parameter = 4.
a) Calculate the probability that a particle enter the counter in a given millisecond?
b) Calculate the probability that 6 particles enter the counter in a given millisecond?
Solution:

Example 6
The average number of typographical error on a single page of statistic textbook is 0.3.
a) What is the probability that exactly two errors on a page.
b) What is the probability that at least one error on a page.
Solution:

QMT 200 NURDIA

5.3.1.1 The Poisson distribution as an Approximation to the Binomial Distribution.

For a random variable with parameters n and p, when the number of trials, n is large and
the success probability, p is small; the Binomial distribution approaches the Poisson
distribution with the parameter given by = np.

In this case = np represents the expected number of successes per unit time or in a
specified region.

Example 7
In a certain industrial facility accidents occur infrequently. It is known that the probability
of an accident on any given day is 0.005 and accidents are independent of each other.
a) What is the probability that in any given period of 400 days there will be an
accident on one day?
b) What is the probability that there are at most three accidents in any period of 400
days?
Solution:

X= no of accidents occur in a period of 400 days , = np=(400)(0.005)=2

QMT 200 NURDIA

Example 8
A certain electronics company manufactures a particular type of electronic device. It is
known that, on the average, two electronic devices out of 100 are defective. The
company packs the electronic devices in boxes of 500.
a) What is the probability that a box of 500 electronic devices will contain r defective
electronic devices?
b) What is the probability that a box of 500 electronic devices will contain at least 3
defectives? (0.9972)
c) What is the probability that a box of 500 electronic devices will contain at most
one defective? (0.4994x10-3 or 11e-10)

Solution:

QMT 200 NURDIA

5.1.4 Geometric Distribution

- Number of trials required until a success is occur.
- If repeated independent trials can result in a success with probability p and a
failure with the probability q = 1 p , then the probability distribution of the
random variable X, the number of trial on which the first success occurs, is

... 3 , 2 , 1 , ) (
1
= =

x pq x f
x

Where p = probability of trials until a success occurs.

Example 9
A box contains 4 red and 6 blue marbles. Marbles are randomly selected, one at a time,
until a blue one is obtained. If we assume that each selected ball is replaced before the
next one is drawn, what is the probability that
a) Exactly n are needed?
b) At most 2 draws are needed?
Solution:

QMT 200 NURDIA

5.1.5 Hypergeometric Distribution

- The Hypergeometric probability distribution is useful for determining the
probability of occurrences when sampling is done without experiment.
- It count the number of successes, x in n trials, where n is fixed, k of which are
successes and (N-k) of which are failures.

Definition
A discrete random variable X is said to have a Hypergeometric distribution with
parameter N, n and k, if its probability density function is given by

k x
n
N
x n
k N
x
k
x f ..., 2 , 1 , 0 ) ( =
|
|
.
|

\
|
|
|
.
|

\
|

|
|
.
|

\
|
=

Where N = size of population
n = size of sample
k = successes
x = number of trials

Example 10
In a box there are 50 chocolates, 10 of which have been tagged with ribbon. If a child
take 7 chocolates, selected at random and without replacement, and X denoted the
number of tagged chocolate, the probability that exactly two tagged chocolates are taken
is
Solution:

QMT 200 NURDIA

Example 11
Exercise (tutorial 5, Q 5.30)
To avoid detection at customs, a traveler places 6 narcotic tablets in a bottle containing
9 vitamins pills that are similar in appearance. If the customs official selects 3 of the
tablets at random for analysis, what is the probability that the traveler will be arrested for
illegal possession of narcotics?
Solution:

5.1.6 Uniform Distribution

- A discrete random variable that assumes each of its values has equal probability.
Such a probability distribution is known as uniform distribution.

Definition
A discrete random variable X, is said to have a uniform distribution with parameter a and
b, if its probability density function is given by

a b
x f

=
1
) ( where x = [a,b]

- Notation: X ~ U(a,b)

- The mean and variance of the Uniform random variable, X is given
by
2
) (
b a
x E
+
= and
12
) (
) (
2
a b
x Var

= respectively.
QMT 200 NURDIA

Example 12
Let X be a random variable which is uniformly distributed over (2,12).
a) Find the pdf of X
b) Calculate the probability that
i. X < 3
ii. X > 10
iii. 4 < X < 7
c) Find the mean and variance of X.
Solution:

QMT 200 NURDIA

5.2.1 The Uniform Distribution

Definition
A random variable X is uniformly distributed on the interval (a, b) with probability density
function is given by

< <

=
elsewhere
b x a
a b
x f
, 0
,
1
) (

Probability of a uniform variable
- If X is a continuous random variable such that X ~ Uniform (a, b), then the
probability of X lies between
2 1
and x x is given by
) (
1

1

) ( ) (
1 2
2 1
2
1
2
1
x x
a b
dx
a b
dx x f x X x P
x
x
x
x

=

=
= s s
}
}

- The mean and variance of the Uniform random variable, X is given
by
2
) (
b a
x E
+
= and
12
) (
) (
2
a b
x Var

= respectively.

QMT 200 NURDIA

Example 13
If a continuous random variable X is uniformly distributed over (3, 8), then find
a) Probability density function of X
b) ) 5 4 ( s s X P
c) ) 5 . 3 ( > X P
d) ) ( and ) ( X Var X E
Solution:

QMT 200 NURDIA

5.2.2 The Normal Distribution

- A variable X is normally distributed with parameter and
2
o id its probability
density function is given by

( )
< < =

x e x f
x
,
2
1
) (
2
2
2o

o t

- Notation ) , ( ~
2
o N X

- The mean and variance of Normal distribution, X is given by ) ( = X E
2
) ( and o = X Var respectively.

Standard Normal Distribution

Definition
The normal distribution with = 0 and
2
o = 1 is called a standard normal distribution.
The probability density function of a standard normal distribution is

2
) 1 ( 2
) 0 (
2
2
2
1
) ( ,
) 1 ( 2
1
) (
x
x
e x f Thus
e x f

=
=
t
t

Definition
If X has a normal distribution with the mean, and variance,
2
o then
o

=
X
Z has a
standard normal distribution.

- The cumulative density function of X is

2
2
1
( )
2
x x
P Z z e dx
t

s =
}

QMT 200 NURDIA

- That is area under the standard normal curve from to x that is equal to the
area to the left of score z. The area can be obtained from Statistical Table, The
Normal Distribution Function.

- Using the Left hand side area, ) ( z Z P s

- Using the Right hand side area, ( ) 1 ( ) P Z z P Z z > = <

Finding area between any given scores

The probability that Z lies between two scores
2 1
and x x
1 2 2 1
( ) ( ) ( ) P x Z x P Z x P Z x s s = s s

Since the normal distribution is symmetry, then
) ( ) (
) ( 1 ) (
x Z P x Z P or
x Z P x Z P
> = s
> = s

z
z
QMT 200 NURDIA

Example 14
Given a random variable X, having a normal distribution with parameter = 65 and
2
o =25, find
a) The probability that X assumes a value between 69 and 72 inclusive.
b) The probability that X more than 71.

Solution:

QMT 200 NURDIA

Example 15
The score of a test is assumed to follow a continuous random variable normally
distributed with = 80 and
2
o =49.

What is the probability that
a) A score chosen at random will be between 85 and 90.
b) A score will be greater than 88.
c) A score will be less than 85.
d) There is a probability of 0.40 that the score of a test more than c. Find the value
of c.
Solution:

QMT 200 NURDIA

Example 16
The waiting time at a particular hospital is approximately normally distributed with a
mean of 3.2 minutes and a standard deviation of 1.5 minutes. The hospital would like to
claim that 95% of all patients are waited on by a hospital attendance within k minutes.
Find the value of k.
Solution:

Approximation Normal to the Binomial Distribution.

- When n is large and ) 1 ( p np is large such that 10 ) 1 ( > p np
- Since Binomial is a discrete random variable and normal is a continuous random
variable, the expression of random variable X is written by
( ) 5 . 0 5 . 0 ) ( + < < = = x X x P x X P this is called continuity correction.
- Four cases:
o ) 5 . 0 ( ) ( < X P x X P
o ) 5 . 0 ( ) ( + s X P x X P
o ) 5 . 0 ( ) ( + > X P x X P
o ) 5 . 0 ( ) ( > X P x X P

QMT 200 NURDIA

Example 17
Given a random variable X, having a binomial distribution with n= 1800, p = 0.4.
a) Find the value of X fewer than 650.
b) ) 750 710 ( < < X P
c) ) 700 ( > X P
Solution:

QMT 200 NURDIA

Approximation Normal to the Poisson Distribution.