Standard
Discrete
Distributions
UNIFORM, BERNOULLI, BINOMIAL
BY DR. GARGI TYAGI
Lecture Highlights
• Uniform Distribution
• Degenerate Distribution
• Bernoulli Distribution
• Binomial Distribution
BY DR. GARGI TYAGI
Uniform Distribution
BY DR. GARGI TYAGI
Consider an experiment of rolling an unbiased die.
Sample space = {1, 2, 3, 4, 5, 6}
𝑋: Number appeared on the die
1
𝑃 𝑋 = 𝑖 = , 𝑓𝑜𝑟 𝑖 = 1, 2, … , 6
6
BY DR. GARGI TYAGI
Tossing a fair coin
Sample Space: Head, Tail
X: Head turns up
10 lottery tickets were distributed to 10 people randomly.
Sample Space: Person 1 to 10 who bought the lottery ticket
X: 𝑥 𝑡ℎ Person wins the lottery, 𝑥 = 1,2, … 10
At what number the ball lands in a roulette wheel spin
Sample Space: Numbers from 1 to 36.
X: Number at which the ball lands
BY DR. GARGI TYAGI
Uniform Distribution
The discrete uniform distribution assumes that all possible outcomes have equal
probability of occurrence.
A discrete random variable 𝑋 with 𝑘 possible outcomes 𝑥1 , 𝑥2 , . . . 𝑥𝑘 is said to
follow a discrete uniform distribution if the probability mass function
(PMF) of 𝑋 is given by
1
𝑃 𝑋 = 𝑥𝑖 = , ∀𝑖 = 1, 2, . . . , 𝑘.
𝑘
BY DR. GARGI TYAGI
Uniform Distribution
If the outcomes are the natural numbers
𝑥𝑖 = 𝑖 (𝑖 = 1, 2, . . . , 𝑘),
1
𝑃 𝑋=𝑖 = , ∀𝑖 = 1, 2, . . . , 𝑘
𝑘
the mean and variance of 𝑋 are obtained as
𝑘+1
𝐸(𝑋) =
2
1 2
𝑉𝑎𝑟 𝑋 = (𝑘 − 1).
12
BY DR. GARGI TYAGI
Uniform Distribution
𝑿 1 2 3 … 𝒌 Total
1 1 1 1
𝑝 𝑥 … 1
𝑘 𝑘 𝑘 𝑘
𝐹(𝑥)
The cumulative distribution function is given as:
𝑖
𝑃 𝑋 ≤ 𝑖 = 𝐹 𝑖 = , 𝑖 = 1, 2, . . . , 𝑘
𝑘
BY DR. GARGI TYAGI
Uniform Distribution
Consider an experiment of rolling an unbiased die.
Sample space = {1, 2, 3, 4, 5, 6}
𝑋: Number appeared on the die
Example
1
𝑃 𝑋 = 𝑖 = , 𝑓𝑜𝑟 𝑖 = 1, 2, … , 6
6
Find 𝐸 𝑋 , 𝑉 𝑋 and the distribution function.
BY DR. GARGI TYAGI
Degenerate Distribution
BY DR. GARGI TYAGI
Degenerate Distribution
A random variable X has a degenerate distribution at 𝑎, if 𝑎 is the only possible
outcome with 𝑃(𝑋 = 𝑎) = 1.
The CDF in such a case is given by
0 𝑖𝑓𝑥 < 𝑎
𝐹 𝑥 =ቊ
1 𝑖𝑓 𝑥 ≥ 𝑎
Further, 𝐸(𝑋) = 𝑎 and 𝑉𝑎𝑟(𝑋) = 0.
The degenerate distribution indicates that there is only one possible fixed outcome,
and therefore, no randomness is involved
BY DR. GARGI TYAGI
Bernoulli Distribution
BY DR. GARGI TYAGI
Bernoulli Distribution
Bernoulli Experiment: An experiment with only two outcomes, success and failure.
Examples:
• A teacher asks one multiple choice question with 4 choices to a student.
• Outcomes: Student gives correct answer or wrong answer.
• A Candidate contesting for an election.
• Outcomes: Win or Lose
• A football player hits a ball towards the goal.
• Outcomes: Makes a goal or does not
BY DR. GARGI TYAGI
Bernoulli Distribution
Examples (cont…):
• A message is transmitted through a machine.
• Outcomes: message received is correct or incorrect.
• A person purchases a lottery ticket.
• Outcomes: Win or Lose
• A candidate appears for a competitive exam.
• Outcomes: Qualifies or Does not qualify
BY DR. GARGI TYAGI
Bernoulli Distribution
A random variable X has a Bernoulli distribution if the PMF of X is given as
𝑝 𝑖𝑓 𝑥 = 1
𝑃 𝑋=𝑥 =ቊ
1 − 𝑝 𝑖𝑓 𝑥 = 0
The cumulative distribution function (CDF) of 𝑋 is
0 𝑖𝑓 𝑥 < 0
𝐹 𝑥 = ൞1 − 𝑝 𝑖𝑓 0 ≤ 𝑥 < 1
1 𝑖𝑓 𝑥 ≥ 1.
BY DR. GARGI TYAGI
Bernoulli Distribution
Moments of Bernoulli Distribution: Moment Generating Function:
𝜇𝑟′ = 𝐸 𝑋 𝑟 = 𝑝, 𝑟 = 1,2, … 𝑀𝑋 𝑡 = 𝑞 + 𝑝𝑒 𝑡
BY DR. GARGI TYAGI
Suppose an experiment consists of 𝒏 independent Bernoulli trials.
BY DR. GARGI TYAGI
Suppose an experiment consists of 𝒏 independent Bernoulli trials.
Example:
• A student takes an MCQ exam consisting of 5 questions. The student is making a
mere guess while answering.
• X: Number of correct answers {0, 1, 2, 3, 4, 5}
• A football player hits a ball 10 times towards the goal.
• X: Number of goals made {0,1,2, … 10}
BY DR. GARGI TYAGI
Binomial Distribution
BY DR. GARGI TYAGI
Binomial Distribution
Conditions of a Binomial Experiment
A binomial experiment must satisfy the following four conditions.
1. There are a finite number of trials.
2. The trials are independent.
3. Each trial has only two possible outcomes (say, success or failure).
4. The probabilities of success remain constant in each trial.
BY DR. GARGI TYAGI
Binomial Distribution
Checking if an experiment is Binomial Experiment
Five percent of all air conditioners manufactured by a large electronics company are defective.
Three air conditioners are randomly selected from the production line of this company.
The selected air conditioners are inspected to determine whether each of them is defective or good.
Is this experiment a binomial experiment?
Conditions of a Binomial Experiment
There are a finite number of trials
The trials are independent
Each trial has only two possible outcomes
The probabilities of success remain constant in each trial
BY DR. GARGI TYAGI
Finding the probability of number of successes
BY DR. GARGI TYAGI
Binomial Distribution
• Let us consider a small binomial experiment with 3 trials.
• The probability of success in each trial is 𝑝
Trial 1 Trial 2 Trial 3 No. of Success Probability No. of Success Probability
S S S 3 𝑝. 𝑝. 𝑝 0
S S F 2 𝑝. 𝑝. 𝑞
1
S F S 2 𝑝. 𝑞. 𝑝
F S S 2 𝑞. 𝑝. 𝑝 2
S F F 1 𝑝. 𝑞. 𝑞
3
F S F 1 𝑞. 𝑝. 𝑞
F F S 1 𝑞. 𝑞. 𝑝
F F F 0 𝑞. 𝑞. 𝑞
BY DR. GARGI TYAGI
Binomial Distribution
The probability of getting 𝑥 success in 𝑛 trials.
BY DR. GARGI TYAGI
Binomial Distribution
A discrete random variable 𝑋 is said to follow binomial distribution with parameters 𝑛
and 𝑝, if its probability mass function is given by
𝑛 𝑥 𝑛−𝑥
𝑝 𝑥 =𝑃 𝑋=𝑥 = 𝑝 𝑞 , 𝑞 = 1 − 𝑝, 𝑥 = 0,1,2, … 𝑛
𝑥
where
𝑛 = The number of trials in an experiment
𝑝 = The probability of success in each trial
𝑋 = The number of successes in 𝑛 trials
𝑃[𝑋 = 𝑥] gives the probability of 𝑥 successes in 𝑛 trials.
BY DR. GARGI TYAGI
Binomial Distribution
Is this function a probability mass function?
𝑛 𝑥 𝑛−𝑥
𝑝 𝑥 =𝑃 𝑋=𝑥 = 𝑝 𝑞 , 𝑥 = 0,1,2, … 𝑛
𝑥
A random variable which follows binomial distribution is known as binomial variate.
It is denoted as 𝑋 ∼ 𝐵(𝑛, 𝑝)
BY DR. GARGI TYAGI
Binomial Distribution
A bag contains 10 chips.
3 of the chips are red, 5 of the chips are white, and 2 of the chips are blue.
Four chips are selected, with replacement.
Example 1
Create a probability distribution for the number of red chips selected.
𝑋 = The number of red chips selected
𝑋 = 0, 1, 2, 3, 4
𝑛 = The number of trials = 4
𝑝 = the probability of selecting a red chip in each trial
3
𝑝=
10
BY DR. GARGI TYAGI
Binomial Distribution
Probability Distribution of Selection of Red Chips
𝑿 𝒑 𝒙 0.5
Example 1
0 0.240 0.4
Probability (p(x))
1 0.412 0.3
2 0.265 0.2
3 0.076 0.1
4 0.008 0
0 1 2 3 4
Number of Red Chips Selected (X)
BY DR. GARGI TYAGI
Binomial Distribution
A department in a works has 10 machines which may need adjustment from time to time during the
day. Three of these machines are old, each having a probability of 1/11 of needing adjustment during
the day, and 7 are new, having corresponding probabilities of 1/21.
Assuming that no machine needs adjustment twice on the same day, determine the probabilities that
Example 2
on a particular day
i) Just 2 old and no new machines need adjustment
ii) If just 2 machines need adjustment, they are of the same type.
Let 𝑋1 = Number of old machines that need adjustment
𝑛1 = Number of old machines (Number of trials) = 3
𝑝1 = probability that an old machine need adjustment = 1/11
𝑋2 = Number of new machines that need adjustment
𝑛2 = Number of new machines = 7
𝑝2 = probability that a new machine need adjustment=1/21
BY DR. GARGI TYAGI
Binomial Distribution
Assuming that no machine needs adjustment twice on the same day, determine the probabilities that
on a particular day
i) Just 2 old and no new machines need adjustment
ii) If just 2 machines need adjustment, they are of the same type.
Example 2
1
𝑋1 = Number of old machines that need adjustment, 𝑋1 ∼ 𝐵 3,
11
1
𝑋2 = Number of new machines that need adjustment, 𝑋2 ∼ 𝐵 7,
21
BY DR. GARGI TYAGI
Binomial Distribution
Assuming that no machine needs adjustment twice on the same day, determine the probabilities that
on a particular day
i) Just 2 old and no new machines need adjustment
ii) If just 2 machines need adjustment, they are of the same type.
Example 2
1
𝑋1 = Number of old machines that need adjustment, 𝑋1 ∼ 𝐵 3,
11
1
𝑋2 = Number of new machines that need adjustment, 𝑋2 ∼ 𝐵 7,
21
BY DR. GARGI TYAGI
Binomial Distribution
In a binomial distribution consisting of 5 independent trials, probabilities of 1 and 2
successes are 0.4096 and 0.2048 respectively. Find the parameter 𝑝 of the distribution.
Example 3
BY DR. GARGI TYAGI
Summary
• Uniform Distribution
• Degenerate Distribution
• Bernoulli Distribution
• Binomial Distribution
BY DR. GARGI TYAGI
In Next Lecture
• Mean and Variance of Binomial Distribution
• Mode of binomial distribution
• Moments of Binomial Distribution
• Recurrence relation for the moments of binomial distribution
• Moment Generating Function of binomial distribution
• Additive Property of binomial distribution
• Characteristic Function
• Cumulants
BY DR. GARGI TYAGI
Thank You
BY DR. GARGI TYAGI
