Probability

Distributions
Discrete Probability Distributions
By: George Mwenye-Phiri
Probability Distributions
• It is the way data are distributed, in order to draw
conclusions about a set of data

• Random Variable = Any quantity or characteristic that is

able to assume a number of different values such that any
particular outcome is determined by chance

• The probability distribution of a random variable is a table,

graph, or mathematical formula that gives the
probabilities with which the random variable takes different
values or ranges of values.
2
Discrete Probability Distributions

• For a discrete random variable, the probability

distribution specifies each of the possible outcomes of
the random variable along with the probability that each
will occur

• Examples can be:

• Frequency distribution
• Relative frequency distribution
• Cumulative frequency
3
Cont.
• We represent a potential outcome of the random
variable X by x

 0 ≤ P(X = x) ≤ 1
 ∑ P(X = x) = 1

4
The following data shows the number of
insurance services a client receives

5
 Cont.

• What is the probability that a customer receives

exactly 3 services?
P(X=3) = 0.031

• What is the probability that a cutomer receives at

most one service?
P (X≤1) = P(X = 0) + P(X = 1)
= 0.671 + 0.229
= 0.900
6
Cont.
• What is the probability that a customer receives
at least four services?
P (X≥4) = P(X = 4) + P(X = 5)
= 0.010 + 0.006
= 0.016

7
Cont.

• Examples of discrete probability distributions are

the binomial distribution and the Poisson
distribution.

8
 Binomial Distribution
• Consider dichotomous (binary) random
variable

• Is based on Bernoulli trial

• When a single trial of an experiment can result
in only one of two mutually exclusive outcomes
(success or failure; defective or not defective,
male or female) 9
 Example:
• We are interested in determining whether a newborn infant will survive
until his/her 70th birthday
• Let Y represent the survival status of the
child at age 70 years
• Y = 1 if the child survives and Y = 0 if he/she does not
• The outcomes are mutually exclusive and exhaustive
• Suppose that 72% of infants born survive to age 70 years
P(Y = 1) = p = 0.72
P(Y = 0) = 1 − p = 0.28

10
 Characteristics of a Binomial
Distribution

• The experiment consist of n identical trials[Fixed].

• Only two possible outcomes on each trial.
• The probability of A (success), denoted by p, remains the
same from trial to trial. The probability of B (failure),
denoted by q,
q = 1- p.
• The trials are independent.
• n and  are the parameters of the binomial distribution.
• The mean is n and the variance is n(1- )
11
 Counting
• Begins with arrangement of objects (permutations)

• May end with combinations (permutation sort of)

 Example: arranging 3 chairs in a
row
• 1st chair can be arranged in 3 ways.
• 2nd of the remaining 2 chairs can be arranged in 2 ways
i.e. (3 – 1) ways
• The 3rd chair can be arranged in 1 way i.e.
(3 – 2) ways
• Total number of ways of arranging the 3 chairs is 3*(3 –
1)*(3 – 2) = 3.2.1 = 3! ways
 Arranging n objects in a row
• N objects can be arranged in n*(n – 1)*(n – 2)*…*(n – (n –
1)) = n*(n – 1)*(n – 2)*…*3.2.1 = n! ways.

• Permutation of n objects = n!

• 10! = 10*9! = 10*9*8! = 10*9*8*7!

• 1! = 0! = 1
 Permutations
• A permutation is a arrangement of objects in a particular
order.
• An arrangement of n objects taken r (ordered) objects at a
time.
• Denoted by nPr
 Permutations
• Question: In how many ways can we arrange 3 chairs A, B,
and C, in ordered pairs?
3 P2 = 6 (i.e. AB, AC, BC, BA, CA, CB)
 Mathematically

3! 3!
3 P2   3!3 * 2 *1 6
(3  2)! 1!
 Combination: n objects, taken r at
a time (order not necessary)
• Question: In how many ways can we arrange 3 chairs A, B,
and C, in pairs?
• This is an arrangement of 3 3 chairs, taken 2 at a time.
 
• Denoted or 3C2 or3C2
 2
3 C2 = 3 (i.e. AB, AC, and BC)
Or
 Mathematically

3! 3! 3! 3 * 2 *1
3 C2     3
2!(3  2)! 2!1! 2! 2 *1
 Note
• If an operation can be performed in m ways, and another
operation can be performed in n ways, then both
operations can be performed in m*n = mn ways
 Example: tossing two dice

• If one die can result in 6 possible outcomes, and another

die can also result in 6 possible outcomes, then the two
dice, tossed together can result in 6 * 6 = 36 possible
outcomes.
 The Binomial Probability
Distribution
• Recall the probability distributions discussed earlier on:
Figure 1: Probability distribution for the number of heads
in one toss, X
Figure 2: Probability distribution for
the number of heads in two tosses, Y
 The Binomial Probability
Distribution (ct)
• Both of the distributions in Figures 1 and 2, above, have
independent Bernouilli trials.

• Therefore called Binomial distributions

 The Binomial Probability
Distribution (ct)
• Suppose we wish to carry out a survey to estimate the
unknown proportion of defective tyres, p, in a population
of tyres using a random sample of n subjects. Suppose r
tyres in the sample are defective.
• Then r is the number of successes that will be used to
estimate the unknown parameter, p.
• Suppose each individual tyre in the sample follows
Bernouilli conditions.
 The Binomial Probability
Distribution (ct)
• Then, each tyre in the sample is a Bernoulli trial (will be
defective– success, or not – failure; has a fixed probability
of having a defect; each tyre will be observed
independently to determine whether they have a defect or
not).
• The number of successes (tyres with defects), r, will follow
a Binomial distribution.
 The Binomial Probability
Distribution (ct) pˆ 
r
n
• The success probability, p, is estimated via a natural
estimator for p, denoted by (p-hat).
40
• ˆ
p
If r = 40, and n = 100, then the estimator,0.40
100
. This is the sample estimate of the true
population parameter, p (the population proportion of
defects). This is the probability that a randomly selected tyre
has a defect.
 The Binomial Probability
Distribution (ct)
• What is the probability of having r successes from n trials?
• Recall that number of ways of selecting (arranging) r
objects from n objects (without order) is given by:

n!
r!( n  r )!
 The Binomial Probability
Distribution (ct)
• Suppose one success occurs with a probability, p, since
the trials are independent, two successes will occur
together with a probability, p * p = p2, three successes,
with a probability p * p * p = p3,…, and any particular
series of r successes will occur with a probability pr. This
means the remaining (n – r) failures, each with a failure
probability, 1 – p, can occur together with a probability
(1 – p) n–r
 The Binomial Probability
Distribution (ct)
• Jointly, all the success and failures can occur together
with a probability, pr (1 – p) n–r

• The probability of r successes from n trials is then given

by: n!
p r (1  p ) n  r
r!( n  r )!
 The Binomial Probability
Distribution
n!
(ct)
n Cr 
• The combination r!(n  r )!

gives the binomial coefficients for the binomial expansion

r n r
p (1  p)
Cont.
• If an experiment is repeated n times and the
outcome is independent from one trial to another,
the probability that outcome A occurs exactly x
times is:
• P (X=x) = , x = 0, 1, 2, ..., n.

36
Cont.
• n denotes the number of fixed trials
• x denotes the number of successes in
the n trials
• p denotes the probability of success
• q denotes the probability of failure (1- p)

• Represents the number of ways of selecting x objects out

of n where the order of selection does not matter.
37
• where n!=n(n-1)(n-2)…(1) , and 0!=1
 Example:
• Suppose we know that 40% of a certain population
of tyres are defective. If we take a random sample
of 10 tyres from this population, what is the
probability that we will have exactly 4 defective
tyres in our sample?

38
Cont.

39