Bernoulli Probability Distribution

• If an experiment has two possible outcomes “success” and “failure”, and their
probabilities are respectively p and 1-p, then the random variable = number of successes
has a Bernoulli Distribution. Note that a success may be getting heads with a balanced
coin, it may be catching pneumonia or it may be losing a race.

• A random variable X has a Bernoulli Distribution and it is referred to as a Bernoulli

Random Variable if and only if its probability distribution is given by

𝑓 𝑥; 𝑝 = 𝑝 𝑥 (1 − 𝑝)1−𝑥 𝑓𝑜𝑟 𝑥 = 0,1

Or
𝑓 𝑥; 𝑝 = 𝑝 𝑥 𝑞1−𝑥 𝑓𝑜𝑟 𝑥 = 0,1 𝑤ℎ𝑒𝑟𝑒 𝑞 = 1 − 𝑝

𝑓 0; 𝑝 = 𝑝0 (1 − 𝑝)1−0 = 1 − 𝑝 = 𝑞: 𝑃𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑜𝑓 𝐹𝑎𝑖𝑙𝑢𝑟𝑒

𝑓 1; 𝑝 = 𝑝1 (1 − 𝑝)1−1 = 𝑝: 𝑃𝑟𝑜𝑏𝑎𝑏𝑖𝑙𝑖𝑡𝑦 𝑜𝑓 𝑆𝑢𝑐𝑐𝑒𝑠𝑠 1

1
 Mean and Variance of a Bernoulli Random Variable
• Mean of a Bernoulli Random Variable:

𝐸 𝑋 = ෍ 𝑥𝑝 𝑥 = 0 1 − 𝑝 + 1 𝑝 = 𝑝

• Variance of a Bernoulli Random Variable:

𝜎 2 = 𝐸 𝑋 2 − (𝐸(𝑋))2

𝐸 𝑋2 = ෍ 𝑥2𝑝 𝑥 = 0 1 − 𝑝 + 1 𝑝 = 𝑝

𝜎 2 = 𝐸 𝑋 2 − (𝐸(𝑋))2 = 𝑝 − 𝑝2 = 𝑝 1 − 𝑝 = 𝑝𝑞

2
2
 Binomial Experiment
An experiment that satisfies the following four conditions is called a Binomial
Experiment:

• The experiment consists of a sequence of n smaller experiments called trials, where n is

fixed in advance of the experiment.

• Each trial can result in one of the same two possible outcomes (dichotomous trials),
which we generically denote by success (S) and failure (F).

• The trials are independent, so that the outcome on any particular trial does not influence
the outcome on any other trial.

• The probability of success P(S) is constant from trial to trial; we denote this probability
by p.

3
3
Example of a Binomial Experiment: Tossing of a balanced coin

Let Success be getting a head

1
P(Success on first trial) =
2

1 1 1 1 1
P(Success on second trial) = P 𝐹𝑆 + 𝑃 𝑆𝑆 = × + × =
2 2 2 2 2

1
Here, 𝑃 𝑆 𝐹 = 𝑃 𝑆 𝑆 = ,
2

i.e. the probability of success i.e. p remains the same irrespective of the outcome in the
previous trial

4
4
Q. Suppose a certain city has 50 licensed restaurants, of which 15 currently have at least one
serious health code violation and the other 35 have no serious violations. There are five
inspectors, each of whom will inspect one restaurant during the coming week. The name of
each restaurant is written on a different slip of paper, and after the slips are thoroughly
mixed, each inspector in turn draws one of the slips without replacement. Label the ith trial
as a success if the ith restaurant selected (i=1,2,3,4,5) has no serious violations. Then

35
P(S on first trial)=
50

P(S on second trial)=P(SS)+P(FS)=P(first S) P(second S|first S) + P(first F).P(second

35 34 15 35
S|first F) = × + ×
50 49 50 49

Here, P(second S|first S) is not equal to P(second S|first F) i.e. the probability of success is
dependent on the outcome of the first trial. Hence, this is not a BINOMIAL
EXPERIMENT

5
5
 Binomial Experiment

• The previous experiment is not binomial because the trials are not independent.

• In general, if sampling is without replacement, the experiment will not yield

independent trials.

• If each slip had been replaced after being drawn, then trials would have been
independent, but this might have resulted in the same restaurant being inspected by
more than one inspector.

6
6
Q. A certain state has 500,000 licensed drivers, of whom 400,000 are insured. A sample of 10
drivers is chosen without replacement. The ith trial is labeled S if the ith driver chosen is
insured. Although this situation would seem identical to the previous example, the important
difference is t hat the size of the population being sampled is very large relative to the sample
size. In this case

399,999
P(S on 2|S on 1)= = 0.8
499,999

400,000
P(S on 2|F on 1)= = 0.8
499,999

399,991
P(S on 10|S on first 9)= = 0.79996 = 0.8
499,991

These calculations suggest that although the trials are not exactly independent, the conditional
probabilities differ so slightly from one another that for practical purposes the trials can be
regarded as independent with constant P(S)=0.8. Thus, to a very good approximation, the
experiment is binomial with n=10 and p=0.8. 7
7
 Rule of Thumb in Deciding Whether a Binomial
Experiment Without Replacement can be Treated as
a Binomial Experiment
Consider sampling without replacement from a dichotomous population of size N. If the
sample size (number of trials) n is at most 5% of the population size, the experiment can be
analyzed as though it were exactly a binomial experiment. The probabilities based on the
binomial experiment assumptions will be quite close to the actual without replacement
probabilities which are typically more difficult to calculated.

In the restaurants question, number of trials (sample size) = 5, Total Population Size = 50
5% of the population size = (0.05)(50)=2.5
Sample Size>5% of Population Size: So Binomial Experiment is not a good approximation

In the drivers question, number of trials (sample size) = 10, Total Population Size =
5,00,000
5% of the population size = (0.05)(5,00,000)=5,000
Sample Size<5% of Population Size: So Binomial Experiment is a good approximation 8
8
 Binomial Random Variable and Probability
Distribution
• In most binomial experiments, it is the total number of successes (S’s), rather than
knowledge of exactly which trials yielded S’s, that is of interest.

• The binomial random variable X associated with a binomial experiment consisting of n

trials is defined as X = the number of successes among the n trials.

• Suppose n=3 for a binomial experiment. Then, there are 8 possible outcomes for the
experiment.

{SSS, SSF, SFS, SFF, FSS, FSF, FFS, FFF}

By definition, X(SSS)=3; X(SFF)=1; X(SSF)=2

9
9
 Binomial Random Variable and Probability
Distribution

• Possible values of X in an n-trial experiment are x=0,1,2,…,n

• We will write: 𝑋~𝐵𝑖𝑛 𝑛, 𝑝 to indicate that X is a binomial random variable based on n

trials with success probability p

10
10
 Probability Distribution or pmf of a Binomial
Random Variable
• Because the pmf of a binomial rv X depends on the two parameters n and p, we denote
the pmf by b(x; n, p).
• Consider the case of n=4. So, x=0,1,2,3,4
S S
S F S F
S S S
S F F S S
F F
S S
S S
F F F F
F S F S
F F

11
11
Probability Distribution of a Binomial Random
Variable

12
12
 Binomial Random Variable and Probability
Distribution
• Suppose we want to find out b(3;4,p) Here x=3; n=4, i.e. we wish to find out what is the
probability of getting 3 successes in 4 trials

• Therefore, b(3;4,p)=P(SSSF)+P(SSFS)+P(SFSS)+P(FSSS)=4𝑝3 1 − 𝑝

13
13
 Binomial Random Variable and Probability
Distribution
• In general,

14
14
 Binomial Random Variable and Probability
Distribution
• Hence, the Probability Distribution or pmf of a binomial random variable is given by:

15
15
 Mean and Variance of a Binomial Random Variable

• Mean of a binomial random variable is given by:

𝑛

𝐸 𝑋 = ෍ 𝑥𝑝 𝑥 = 𝑛𝑝
𝑥=0

• Variance of a binomial random variable is given by:

2 2
𝑉 𝑋 =𝐸 𝑋 − 𝐸 𝑋 = 𝑛𝑝𝑞

18
18
 Cumulative Binomial Probabilities

• Even for a relatively small value of n, the computation of binomial probabilities can be
tedious.
• The Cumulative Binomial Tables tabulate the cdf 𝑃 𝑋 ≤ 𝑥 for n=5, 10, 15, 25 in
combination with the selected values of p.

30
30
Cumulative Binomial Probabilities: Illustration

31
31
 Binomial Distribution: Numericals
Q. A particular type of tennis racket comes in a midsize version and an oversize version.
Sixty percent of all customers at a certain store want the oversize version.

a. Among ten randomly selected customers who want this type of racket, what is the
probability that at least six want the oversize version?

b. Among ten randomly selected customers, what is the probability that the number who
want the oversize version is within 1 standard deviation of the mean value?

c. The store currently has seven rackets of each version. What is the probability that all of
the next ten customers who want this racket can get the version they want from current
stock?

32
32
 Binomial Distribution: Numericals
Ans a. 𝑝 = 0.6, 𝑞 = 0.4

𝑃 𝑋 ≥ 6 = 1 − 𝑃 𝑋 ≤ 5 = 1 − 𝐵 5; 10,0.6 = 1 − 0.367 = 0.633

b. Mean = np=(10)(0.6)=6
Variance = npq = (10)(0.6)(0.4)=2.4
Standard Deviation = 2.4 = 1.55

The probability that X is within one standard deviation of its mean value

𝑃 6 − 1.55 ≤ 𝑋 ≤ 6 + 1.55 = 𝑃 4.45 ≤ 𝑋 ≤ 7.55 = 𝑃 5 ≤ 𝑋 ≤ 7 = F 7 − F 4

= B 7; 10,0.6 − B 4; 10,0.6 = 0.833 − 0.166 = 0.667

33
33
Ans c. 𝐿𝑒𝑡 𝑋 = 𝑡ℎ𝑒 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑝𝑒𝑜𝑝𝑙𝑒 𝑤ℎ𝑜 𝑤𝑎𝑛𝑡 𝑡ℎ𝑒 𝑜𝑣𝑒𝑟 − 𝑠𝑖𝑧𝑒𝑑 𝑣𝑒𝑟𝑠𝑖𝑜𝑛
Oversized Version (X) Mid-Sized Version Possible/Not Possible
0 10 Not Possible

1 9 Not Possible
2 8 Not Possible
3 7 Possible
4 6 Possible
5 5 Possible
6 4 Possible
7 3 Possible
8 2 Not Possible
9 1 Not Possible
10 0 Not Possible

Hence, the possible values of X are 3,4,5,6 and 7

𝑃 3 ≤ 𝑋 ≤ 7 = F 7 − F 2 = B 7; 10,0.6 − B 2; 10,0.6 = 0.833 − 0.012 =

= 0.821 34
34