Discrete random variables and

their probability distribution

• Any given statistical experiment has more than one outcome.
• It is impossible to predict which of the many possible outcome will
occur if an experiment is performed.
• Consequently, decisions are made under certain conditions.
• For example: A lottery player does not know in advance whether or
not he is going to win that lottery. If he knows that he is not going to
win, he will definitively not play. It is the uncertainty about winning
(same positive probability of winning) that makes him play.
• This lection shows that if the outcomes and their probabilities for a
statistical experiment are known, we can find out what will happen,
on average, if that experiment is performed many times.
Random variables
Nr of vehicles Frequency FR
owned by Suppose one family is randomly selected from
families (x) this population. The process of randomly
0 30 30/2000=0.015 selecting a family is called a random or chance
experiment.
1 470 0.235
X- nr of vehicles owned by families
2 850 0.425
The value assumed by x – on which family is
selected.
3 490 0.245 This value depends on the outcome of a random
experiment.
4 160 0.080
X- random variable OR a chance variable
Total 2000 1.000
Random Variable
• is a variable whose value is determined by the outcome of a random
experiment
Probability distribution of a
discrete random variable
Probability distribution of a discrete random
variable

• The probability distribution of a discrete random variable lists all the

possible values that the random variable can assume and their
corresponding probabilities.
Frequency and Relative Probability distribution of the
Frequency distribution of the nr nr of vehicles owned by
of vehicles owned by families families

Nr of vehicles Frequency FR Nr of vehicles Probability

owned by owned by P(x)
families (x) families (x)
0 30 30/2000=0.015 0 0.015

1 470 0.235 1 0.235

2 850 0.425 2 0.425

3 490 0.245 3 0.245

4 160 0.080 4 0.080

Total 2000 1.000 Total 1.000

The probability distribution of a discrete random variable possesses the following
two characteristics:

• The probability assigned to each value of a random variables x lies in

the range 0 to 1; that is
0 ≤ P(x) ≤ 1 for each x

• The sum of the probabilities for all possible values of x is equal to 1.

Σ P(x) = 1
Probability distribution of the nr of vehicles
owned by families
Nr of vehicles Probability
owned by (P(x)
families (x)
0 0.015

1 0.235

2 0.425

3 0.245

4 0.080

Total 1.000
Each of the following tables lists certain values of x and their probabilities.
Determine whether or not each table represents a valid probability distribution.

x (P(x) x P(x) x P(x)

0 0.08 0 0.25 0 0.70

1 0.11 1 0.34 1 0.50

2 0.39 2 0.28 2 -0.20

3 0.27 3 0.13
Factorials
Factorial - !
• Is used to denote factorials
• The value of the factorial of a number is obtained by multiplying all
the integers form that number to 1.

7! = 7 . 6 . 5 . 4 . 3 . 2 . 1 = 5040
Definition
• The symbol n!, read as “n factorial” represents the product of all the
integers form n to 1.

n! = n(n-1)(n-2)(n-3)……3 . 2 . 1

By definition: 0!=1
Combinations
• Quate often we face the problem of selecting a few elements from a
large number of distinct elements.
• For example: a student is required to attempt any two questions out
of four in an examination.
• How many possible selections exist for the student who is to choose
any two questions out of four?

(1 and 2), (1 and 3), (1 and 4), (2 and 3), (2 and 4), (3 and 4)
 • Each of the possible selection in this list is called a combination. All six
combinations are distinct; that is each combination contain a
different set of questions

Combinations give the number of ways x elements can be selected from n

elements. The notation used to denote the total number of combination is
nCx

which is read “the number of combination of n elements selected x at a

time” .
n denotes the total number of elements

C
n x

x denotes the number of elements

selected per selection
The nr of combinations for selecting x from n
elements is:

n!
n Cx
=
x! (n-x)!
 Example:
• Three members of a jury will be randomly selected from five people.
How many different combinations are possible?

n=5, x=3

5! 5.4.3.2.1 120
C
n x = = = = 10
3! (5-3)! 6.2 12
The binomial probability
distribution
The binomial distribution (BD)
• Is one of the most widely used discrete probability distributions.
• It is applied to find the Prob that an outcome will occur x time in n performances
of an experiment.

• The random variable x MUST be a discrete dichotomous variable – the variable

must be a DRV and each repetition of the experiment must result in one of two
possible outcomes.

• Each repetition of a binomial experiment is called a trial or Bernoulli trial.

• The BD is applied to the experiments that satisfy the 4 conditions of a binomial

experiment.
4 conditions of a binomial experiment
1. There are n identical trials (the given experiment is repeated n
times. All these repetitions are performed under identical
conditions).
2. Each trial has two and only two outcomes.
3. The probability of two outcomes remain constant.
4. The trial are independent.

An experiment that satisfies 4 conditions is called a binomial

experiment.
The probability

• p- probability to have the outcome of interest ( P of success)

• q- probability to have the other outcome ( P of failure)

Remember:

p+q=1
 BD is applied to find the Probability of x successes in n trials for
a binomial experiment

p xqn− x
n!
ƒ(r) =
x!(n - x)! n = total nr of trials
p = Prob of success
q = 1- p = Prob of failure
x = nr of successes in n trials
n-x = number of failures in n
trials
 Distribuzione binomiale

• 23% of all Albanian population suffer from HTA (Albanian DHS, 2008-
09).

• We can quantize the probabilities relative to the outcome respects of

x as:
P(x=1, HTA) = p = 23% = 0.23

P(x=0, no HTA) = 1 - p = 1-0.23 = 0.77

23% of all Albanian population suffer from
HTA (Albanian DHS, 2008-09).

• Suppose we randomly select three subjects from the Albanian population.

• What is the probability that exactly one of these three is suffering from HTA.
• If we introduce a new causal variable X that represents the number of subjects in
each single copy who are hypertensive, then X can take on three values: 0, 1, 2.
• 0 - or both selected subjects are not hypertensive,
• 1 - either one is hypertensive and the other is not,
• 2 - or both are hypertensive.
 Results P of these Number of
1st 2nd subject results hypertensiv
• .The attitudes towards subject es
blood pressure of the two
0 0 (1-p)(1-p) 0
selected subjects are
independent, we can apply
the product principle to 1 0 p (1-p) 1
calculate the probability
that X will take on a certain 0 1 (1-p) p 1
value.
1 1 pp 2
 Results P of these Number of P-value
1st subject 2nd subject results hypertensive
s

0 0 (1-p)(1-p) 0 (0.77)2=0.5929

1 0 p (1-p) 1

0 1 (1-p) p 1

1 1 pp 2
 Results P of these Number of P-value
1st subject 2nd subject results hypertensive
s

0 0 (1-p)(1-p) 0 (0.77)2=0.5929

1 0 p (1-p) 1 (0.23)(0.77)=0.1771

0 1 (1-p) p 1 (0.77)(0.23)=0.1771

1 1 pp 2 (0.23)2=0.0529
 H– HTA
N – no HTA
HH = (0.23)2
H

H HN = (0.23) (0.77)
HN

sample NH = (0.77) (0.23)

NH

NN
NN = (0.77)2
 Risultato di Y P di questi Numero di Valore di P
1 2 3 soggetto risultati ipertensi
soggetto soggetto

0 0 0 (1-p) (1-p) (1-p) 0 0.457

1 0 0
0 1 0
0 0 1
1 1 0
1 0 1
0 1 1
1 1 1

Totale
 Results P of these Number of P-value
1st 2nd 3rd subject results hypertensiv
subject subject es

0 0 0 (1-p) (1-p) (1-p) 0 0.457

1 0 0 p (1-p) (1-p) 1 0.136
0 1 0 (1-p) p (1-p) 1 0.136
0 0 1 (1-p) (1-p) p 1 0.136
1 1 0 pp (1-p) 2 0.041
1 0 1 p (1-p) p 2 0.041
0 1 1 (1-p) pp 2 0.041
1 1 1 ppp 3 0.012

Totale 1.0
 1st person 2nd person 3rd person

HHH

HH

HHN

H HNH

HN
HNN

sample
NHH
NH

NHN
N

NNH

NN
H – HTA
NNN
N – no HTA
Remember
• To find the probability of x successes in N trials for a binomial
experiment, the only values needed are those
n and p

These are called the parameter of the binomial probability distribution

or binomial parameters.
Exercise
• According to Gallup study, 10% of Americans said that they had
gained “a lot” of weight in the past five years. Assume that this result
is true for the current American population, find the probability that
in a random sample with 4 American people,the number who will say
they had gained “a lot” of weight in the past five years is
• exactly 2
• less than three.