Statistics-1

Section (7)
Prepared By : Doaa Ghaleb
 Special Probability Distribution
● Probability Distribution: It is a listing of the probabilities of all the possible
outcomes that could occur if the experiment was done.

Discrete Probability Continuous Probability

Distribution Distribution
1- Binomial ( Bernoulli ) 1- Uniform
2- Hypergeometric 2- Normal
3- Poisson 3- Exponential
4- Negative Binomial
5- Geometric
Probability Distribution for Discrete Random Variable

A coin tossed 3 times what is the probability distribution of No. of heads.

3 2 2 2 1 1 1 0
S = { HHH , HHT , HTH , THH , HTT , THT , TTH , TTT } X frequency P(X)

Let X represents “No. of heads” 0 1

⅛
1 3
⅜
X 0 1 2 3 2 3
⅜
P(X)
⅛ ⅜ ⅜ ⅛ 3 1
⅛
Probability Distribution for Discrete Random Variable

A coin tossed 4 times what is the probability distribution of No. of heads.

4 3 3 3 3 2 2
S = { HHHH, HHHT, HHTH, HTHH, THHH, HHTT, HTHT,

2 2 2 2 1 1 1 1 0
THHT, THTH, TTHH, HTTH, TTTH, TTHT, THTT, HTTT, TTTT}

Let X represents “No. of heads”

x 0 1 2 3 4

P(x) 1/16 4/16 6/16 4/16 1/16

 1 - Binomial Distribution
Binomial Distribution : is a generalization of Bernoulli trials. It's the distribution that
describes the probability for number of successes in a sequence of n independent
Bernoulli trials regardless of the order in which they occur.

1- The experiment consists of n repeated Finite trials.

2- The repeated trials are independent.
3- The outcome in each trial classified as a success or a failure.
Examples : (heads/tails,correct/erroneous bits, good/defective items, active/silent
speakers)
4- The probability of success is constant and denoted by p and probability of failure
also are constant donated by q

→ The random variable x is said to follow binomial distribution this can be written as :

x ~ Bin ( n , p )
 How to get p and q ?
● “Tossing of Coin” experiment:

S= {Head, Tail} → x represents number of head

½ ½
● “Tossing of Die”experiment
S= {1, 2, 3, 4, 5, 6}

⅙ ⅙ ⅙ ⅙ ⅙ ⅙
 How to get p and q ?
● “Tossing of Coin” experiment:

S= {Head, Tail} → x represents number of head

P(Head) = ½
q(Tail) = 1 - ½ =½

● “Tossing of Die”experiment

S= {1, 2, 3, 4, 5, 6} → x represents number 5 occur

P(number 5 ) = ⅙
q(any other number) = 1 - ⅙ = ⅚
 1 - Binomial Distribution
Binomial Distribution : is a generalization of Bernoulli trials. It's the distribution
that describes the probability for number of successes in a sequence of n
independent Bernoulli trials regardless of the order in which they occur.

● n : number of trials
● p : probability of success
● q : probability of failure q = 1- p
→ The random variable x is said to follow binomial distribution this can be
written as :

x ~ Bin ( n , p )
 Example
A coin tossed 4 times what is the probability that # of head occur

1) Finite 2) Probability is constant 3) Independent

X : is # of head
● X : number of success in sample x=0,1,2,....n
● n : number of trials (sample size)
● p : probability of success
● q : probability of failure q = 1- p
→ The random variable x is said to follow binomial distribution this can be
written as :

x ~ Bin ( n , p )
1- Binomial Distribution
 Example (1)
Flip a coin 4 times . Find the probability distribution of # of heads .

n=4

x= 0 , 1 , 2 , 3 , 4
p= ½
q = 1-p =1- ½ =½
{HTTT,
……….,
………...} x 0 1 2 3 4

P(x) 1/16 4/16 6/16 4/16 1/16

 Example (1)
A fair coin toss 10 times . Find the probability of Getting :

1- Exactly 3 heads

n=10

x=3
p= ½
q = 1-p =1- ½ =½
{HTTHTTHTTT,
…………………,
………………..}
 Example (1)
A fair coin toss 10 times . Find the probability of Getting :

2- At least 9 heads

n=10

x= 9 , 10
p= ½
q = 1-p =1- ½ =½
 Example (1)
A fair coin toss 10 times . Find the probability of Getting :

3- At least 2 heads

n=10

x=2,3,4,5,6,7,8,9,10
p= ½
q = 1-p =1- ½ =½
 Example (1)
A fair coin toss 10 times . Find the probability of Getting :

4- At most 1 head

n=10

x= 0 , 1
p= ½
q = 1-p =1- ½ =½
 Example (1) - try it with yourself
A fair coin toss 10 times . Find the probability of Getting :

5- At least 4 given at most 1

n=10

x= ?!
p= ½
q = 1-p =1- ½ =½
 Example (1)
A fair coin toss 10 times . Calculate E(x) , V(x) , Standard deviation

n=10
p=½
q=½
 Example (2)
Find the probability that seven of 10 persons will recover from a tropical
disease if we can assume independence and the probability is 0.80 that any one
of them will recover from the disease.

n=10

x=7

p = 0.8

q = 1-p =0.2
 Example (2)
Find the probability that seven of 10 persons will recover from a tropical
disease if we can assume independence and the probability is 0.80 that any one
of them will recover from the disease . Calculate the mean and the variance.

n=10

p = 0.8

q = 1-p =0.2
 2- Bernoulli Distribution

Bernoulli Trials describe an experiment that consists of the following

characteristics :
Bernoulli probability Fn() :
1- Finite n=1 trials.
2- Trials are independent. P(x=0) = 1-p = q
Success (p) P(x=1) = p
3- Outcome
Failure (q = 1-p)

x=1 Success
4- x
x=0 Failure
2- Bernoulli Distribution
Proves Bernoulli Distribution Rules
 Example (1)
Suppose a dice is thrown once and we have random variable X , such that If
Number 6 appears , then X =1 , else X =0
P
Probability that 6 appears (Success ) =

q
Probability that 6 don’t appears (Failure )=
 Example (1)
Suppose a dice is thrown and we have random variable X , such that If Number
6 appears , then X =1 , else X =0 .

Calculate the mean and the variance

 3- Hypergeometric Distribution
The Hypergeometric Distribution :

1. Has “ n “ trials in a sample taken from a finite population of size “ N “

2. Sample taken without replacement
3. Outcomes of trials are dependent
4. Concerned with finding the probability of “X” successes in the sample
where there are “A” successes in the population

→ The random variable x is said to follow hypergeometric distribution this can be

written as :

x ~ Hyp ( n , A ,N )
Hypergeometric Distribution vs. Binomial Distribution

● The Hypergeometric distribution is a discrete probability distribution

that describes the probability of successes in draws from a finite
population of size containing :
1) Successes without replacement
2) Trials are dependent.

● It differs from Binomial distribution, which describes the probability of:

1) Successes in draws with replacement
2) Trials are independent.
 3 - Hypergeometric Distribution

Sample

x = ?! n=6

Where :

N = population size
A = number of successes in the population A = 15 N-A = 5
N – A = number of failures in the population
n = sample size
x = number of successes in the sample N = 20
n - x = number of failures in the sample
Population
3 - Hypergeometric Distribution
 Why population and sample in Hypergeometric
Distribution ?!
On the binomial and other discrete distribution, we didn't use
the population and used instead the probabilities , that's
because in the previous distribution, they were all with
replacement.

So, probabilities were constant and it was just a matter of

different distribution cases. As for hypergeometric, It's
without replacement distribution, meaning that after each one
sampling, the probability will change , that's why it uses the
population in the equation.
3- Hypergeometric Distribution
 Example (1)

A box contains 10 electric bulbs from which 4 bulbs are defective. Three bulbs
are chosen at random without replacement from box . What is the probability
that one of them is defective?

N=10 → n=3
A=4 → x=1
N-A = 6 → n-x = 2
 Example (1)

Sample

x=1 n=3

A box contains 10 electric bulbs from which 4

bulbs are defective. Three bulbs are chosen at
random without replacement from box . What A=4 N-A = 6
is the probability that one of them is defective?

N=10 → n=3
N = 10
A=4 → x=1
N-A = 6 → n-x = 2
Population
 Example (2)

A bag contains 100 white balls and 200 red balls. A random sample of 5 is
taken without replacement. Find the probability that exactly three out of 5 will
be white.

N=300 → n=5
A=100 → x=3
N-A = 200 → n-x = 2
 Example (1)

Sample

x=3 n=5

A bag contains 100 white balls and 200 red

balls. A random sample of 5 is taken without
replacement. Find the probability that exactly A = 100 N-A = 200
three out of 5 will be white.

N=300 → n=5
N = 300
A=100 → x=3
N-A = 200 → n-x = 2
Population
 Example (2)

A bag contains 100 white balls and 200 red balls. A random sample of 5 is
taken without replacement. Find the probability that exactly three out of 5 will
be white.Calculate E(x) , V(x) ?
 4 - Poisson Distribution
Poisson Distribution is a probability distribution that expresses the probability of
a given number of events occurring in a fixed disjoint interval of time and/or
space if these events occur with a known average rate and independently of the
time since the last event.

1. Independent trials
2. Probability of success P(x) constant
3. Trials are infinite (N)
4. P(x) is very small and N is very large.

→ Keywords : Average( ),P(x) is very small and N is very large.

 Remember : Binomial Distribution
Remember that :
1- The experiment consists of n repeated Finite trials.
2- The repeated trials are independent.
3- The outcome in each trial classified as a success or a failure.
Examples : (heads/tails,correct/erroneous bits, good/defective items, active/silent
speakers)
4- The probability of success is constant and denoted by p and probability of failure
also are constant donated by q

→ The random variable x is said to follow binomial distribution this can be written as :

x ~ Bin ( n , p )
 4 - Poisson Distribution
The Poisson Distribution :

1- The experiment consists of n repeated infinite trials.

2- The repeated trials are independent.
3- The probability of success is constant and denoted by p(x) → (very small)

● P(x): very small

● N trials :very large (infinite)
● : the average number of events / unit = P*N = E(x)=V(x)
→ The random variable x is said to follow poisson distribution this can be written as :

x ~ Poisson ( lambda )
 4 - Poisson Distribution

When to use Poisson Distribution ?!

● If we want to study the occurrence of an event during specific period of

time or within a given distance area value.

● If the probability of occurrence an event is very rare to happen p(x) very

small and N is very large (eg. accedinets )

● When it give you an event with average of its occurrence

4 - Poisson Distribution
Example (1)
 Example (2)

Records show the probability is 0.00005 that a car will have flat tire while
crossing a certain bridge , Find the probability that exactly two cars will
have a flat tires among 10000 cars crossing the bridge.
 Example (2)

Records show the probability is 0.00005 that a car will have flat tire while
crossing a certain bridge , Find the probability that exactly two cars will
have a flat tires among 10000 cars crossing the bridge.Calculate the mean
and the variance .
 Example (3)

Number of patients admitted to ICU for the university hospital per day.
If the average persons admitted to ICU per day is 3.

(1) What is the probability that in a given day there will be exactly 2
admissions ?
(2) What is the probability that in a given day there will be at most 2
admissions ?
(3) What is the probability that in a given week there will be exactly 7
admissions ?
 Example (3)

Number of patients admitted to ICU for the university hospital per day.
If the average persons admitted to ICU per day is 3.

(1) What is the probability that in a given day there will be exactly 2
admissions ?
 Example (3)

Number of patients admitted to ICU for the university hospital per day.
If the average persons admitted to ICU per day is 3.

(2) What is the probability that in a given day there will be at most 2
admissions ?
 Example (3)

Number of patients admitted to ICU for the university hospital per day.
If the average persons admitted to ICU per day is 3.

(3) What is the probability that in a given week there will be exactly 7
admissions ?
 Special Probability Distribution
Binomial Distribution Bernoulli Distribution

1- n Finite trials. 1- n=1 trial.

2- Independent / with replacement 2- Independent.
3- The probability of success is 3- There are ONLY two values for the
constant (p) and the probability of random variable either :
failure also is constant (q=1-p) x=1 (success) or x=0 (failure)
4- x represents number of success P(x=1)= p and P(x=0) = q
4- x represents number of success
 Special Probability Distribution
Hypergeometric Distribution Poisson Distribution
1- n Finite trials. 1- NOT Finite trials(N).
2- Dependent / without replacement 2- P(x) is very small and N is very large.
3- Consists of Population and Sample 3- Independent.
Keywords : without replacement , the Keywords : Average( ),P(x) is very
experiment divided to : sample and small and N is very large.
population 4- x represents number of success
4- x represents number of success
 5 - Geometric Distribution

Definition of Geometric Distribution

In a series of Bernoulli trial (independant and trials with constant probability

P of success) let the random variable x denotes the # of trials until the 1st
success then x is a geometric random variable with probability 0 ≤ P(x) ≤ 1

Is a special case of the negative binomial distribution, It deals with the

number of trials required for a single success. Thus, the geometric
distribution is the negative binomial distribution where the the number of
successes equal to 1 (r =1)
 5 - Geometric Distribution
P P( x=1)
P( x=2)
Goal of Geometric ?! P
P
P( x=3)
To Get the 1st Success after how many trials q
q

→ x random variable : # of trials q

5 - Geometric Distribution
 Example (1)

If the probability of hitting a target in a single shot is 0.7 , if shots are be fair
far at the target independently . what is the probability that 1st hit to the
target will be in :

(a) 3rd shot .

The random variable x → represent # of trials

 Example (1)

If the probability of hitting a target in a single shot is 0.7 , if shots are be fair
far at the target independently . what is the probability that 1st hit to the
target will be in :

(b) 5th shot .

The random variable x → represent # of trials

 Example (2)

If the probability is 0.40 that a child exposed to a certain disease will catch
it,what is the probability that the 10th exposed to the disease will be the first
to catch it , calculate the expected value and the variance .

The random variable x → represent # of trials

 Example (3)--> Try it with yourself

A coin tossed , what is the probability that the 1st head occurs at 10th trial ?

The random variable x → represent # of trials

 6- Negative Binomial Distribution

Definition of Negative Binomial Distribution (R-Success)

In a series of Bernoulli trials (independant and trials with constant probability

P of success) let the random variable x denotes the # of trials until r
successes then x is a negative binomial random variable with probability 0 ≤
P(x) ≤ 1
Wit parameters r = 1,2,3 ,.... And x = r , r+1 , ….
6 - Negative Binomial Distribution
 Example
Flip a coin 4 times . Find the probability of 1 head occur .

n=4 , x= 1 , p = ½ , q = 1-p =1-½ =½ Binomial

Flip a coin 4 times . Find the probability that the 1st head occurs at 3rd trial
n=4 , x= 3 , p = ½ , q = 1-p =1-½ =½ Geometric

Flip a coin 4 times . Find the probability of getting 2 heads at 3rd trial.
n=4 , x= 3 , r = 2 , p = ½ , q = 1-p =1-½ =½
-ve Binomial
 Example (1)

If the probability is 0.40 that a child exposed to a certain disease will catch
it,what is the probability that the 10th exposed to the disease will be the
third to catch it.
 Example (2)--> Try it with yourself

In a clinical study , volunteers are tested for a gene that has been found to
increase the risk for a disease . The probability that a person carries the
gene is 0.1.

(a) What is the probability that 4 or more people will have to be tested
before 2 with the gene are detected

The random variable x → represent # of trials

 Special Probability Distribution
Geometric Distribution Negative Binomial Distribution
1- x represents the number of trials 1- x represents the number of trials
2- n finite trials. 2- n finite trials.
2- Independent / with replacement 2- Independent / with replacement
3- The probability of success is 3- The probability of success is
constant (p) and the probability of constant (p) and the probability of
failure also is constant (q=1-p) failure also is constant (q=1-p)