COURSE: Math 13 Engineering Data Analysis

TOPIC 3: DISCRETE PROBABILITY DISTRIBUTION

Title Learning Outcomes

Topic “I SHOULD BE ABLE TO”… Estimated
time
III 3.1. What Is DISCRETE 1. Define discrete probability distribution. 12 hours
PROBABILITY 2. Determine probabilities from cumulative
DISTRIBUTION? distribution functions and
3.2. Discrete Probability cumulative distribution functions from
Distribution Example probability mass functions, and the
3.3. Discrete Probability reverse.
Distribution Formula 3. Calculate means and variances for
3.4. Discrete Probability discrete random variables
Distribution PMF 4. Understand the assumptions for some
3.5. Discrete Probability common discrete probability distributions
Distribution CDF 5. Select an appropriate discrete
3.6. Discrete Probability probability distribution to calculate
Distribution Variance probabilities in specific applications
3.7. Discrete Probability 6. Calculate probabilities, determine
Distribution Types means and variances for some
3.7.1. Bernoulli common discrete probability distributions
Distribution 7. Use the table for the
3.7.2. Binomial cumulative distribution function of a
Distribution standard normal distribution to
3.7.3. Geometric calculate probabilities
Distribution
3.7.4 Poisson
Distribution
3.8. How To Find
Discrete Probability
Distribution?

Study
3.1. What Is DISCRETE PROBABILITY DISTRIBUTION?
A discrete distribution is a way of describing the likelihood of individual, separate outcomes
happening. These outcomes could be things like numbers (1, 2, 3), yes or no answers, or true and
false statements. For instance, if you're flipping a coin multiple times, a discrete distribution helps us
understand the chance of getting heads or tails.

There are two main types of statistical distributions: discrete and continuous. Discrete distributions
deal with outcomes that you can count individually, like the examples mentioned earlier. On the other
hand, continuous distributions involve outcomes that exist along a range, like all the numbers
between 0 and infinity.

A discrete probability distribution is basically a way to figure out the chances of getting certain values
with something that can't be divided up infinitely, like counting the number of times you get heads
when flipping a coin. It's all about calculating the likelihood of specific outcomes happening, but it's
important to note that these outcomes are limited to a certain, countable number.

To make sure a distribution is considered discrete, it needs to meet two specific conditions, which
are:

• 0 ≤ P(X = x) ≤ 1. This implies that the probability of a discrete random variable, X, taking on
an exact value, x, lies between 0 and 1.
• ∑P(X = x) =1. The sum of all probabilities must be equal to 1.

3.2. Discrete Probability Distribution Example

Suppose a fair dice is rolled and the discrete probability distribution has to be created. The possible
outcomes are {1, 2, 3, 4, 5, 6}. Thus, the total number of outcomes will be 6. All numbers have a fair
chance of turning up. This means that the probability of getting any one number is 1 / 6. Using this
data the discrete probability distribution table for a dice roll can be given as follows:

Imagine rolling a fair six-sided die and you want to figure out how likely it is to get each number. The
possible outcomes are 1, 2, 3, 4, 5, and 6. So, you have a total of 6 possible outcomes. Since the die
is fair, each number has an equal chance of showing up.

That means the probability of rolling any specific number is 1 out of 6, because there are 6 equally
likely outcomes when you roll the die.

With this information, you can create a table to show the discrete probability distribution for rolling the
die, see Table 3.1
Table 3.1. Discrete probability distribution table for a dice roll

3.3. Discrete Probability Distribution Formula

When we talk about a discrete random variable, we're basically describing something that can take
on specific values with certain probabilities. Think of it like rolling a six-sided die, where you know
you'll get a number from 1 to 6, each with its own chance of happening.

Now, there are two important functions tied to this kind of random variable. First, there's the
probability mass function, or PMF for short. This function tells us the probability of getting a particular
value. It's like a recipe that shows how likely each outcome is.
The second function is called the cumulative distribution function, or CDF. This one gives us the
probability of getting a value less than or equal to a certain number. It's like adding up all the
probabilities as you move along the possible values.

So, these functions help us understand how likely different outcomes are when we're dealing with a
discrete random variable. They're like tools that help us navigate the world of probabilities.

3.4. Discrete Probability Distribution PMF

The probability mass function (PMF) is a mathematical tool used to calculate the probability of a
discrete random variable, denoted as X, having a specific value, x. It's a crucial component when
constructing a discrete probability distribution. The formula for the PMF is defined as follows:

f(x) = P(X = x)

3.5. Discrete Probability Distribution CDF

The average of a discrete probability distribution represents the weighted sum of all potential values
of the discrete random variable. This average is also referred to as the expected value. The formula
for calculating the mean of a discrete random variable is as follows:

E[X] = ∑x P(X = x)

3.6. Discrete Probability Distribution Variance

The variance of a discrete probability distribution measures how spread out the distribution is around
the mean. It represents the average of the squared differences between each value in the distribution
and the mean, denoted as μ. The formula for calculating the variance is provided below:

Var[X] = ∑(x - μ)2 P(X = x)

3.7. Discrete Probability Distribution Types

In a Monte Carlo simulation, a discrete probability distribution helps determine the likelihood of
various outcomes occurring. Below are the most frequently utilized types of discrete probability
distributions.

3.7.1. Bernoulli Distribution

A Bernoulli distribution is a type of a discrete probability distribution where the random variable can
either be equal to 0 (failure) or be equal to 1 (success). The probability of getting a success is p and
that of a failure is 1 - p. It is denoted as X ∼ Bernoulli (p). The pmf is expressed as follows:

3.7.2. Binomial Distribution

A binomial distribution is a discrete probability distribution that gives the success probability in n
Bernoulli trials. The probability of getting a success is given by p. It is represented as X ∼ Binomial(n,
p). The pmf is given as follows:

3.7.3. Geometric Distribution

A geometric distribution is another type of discrete probability distribution that represents the
probability of getting a number of successive failures till the first success is obtained. It is given by X
∼ G(p). The formula for the pmf is given as follows:

3.7.4 Poisson Distribution

Poisson distribution is a discrete probability distribution that is widely used in the field of finance. It
gives the probability that a given number of events will take place within a fixed time period. The
notation is written as X ∼ Pois(λ), where λ>0. The pmf is given by the following formula:

3.8. How To Find Discrete Probability Distribution?

A discrete probability distribution can be depicted through either a table or a graph. To establish a
discrete probability distribution, one needs the probability mass function, which entails all the values
of the discrete random variable along with their respective probabilities. Let's consider an example
where a fair coin is tossed twice to determine the number of heads observed. The process involves
the following steps:

• Step 1: Establish the sample space of the experiment. When a fair coin is tossed twice, the
sample space includes outcomes such as {HH, HT, TH, TT}, where H signifies heads and T
denotes tails. Hence, the total number of outcomes equals 4.
• Step 2: Introduce a discrete random variable, X. In this case, let X denote the number of
heads observed.
• Step 3: Determine the possible values that the variable can take. There are 3 potential values
for X: 0 (no heads observed), 1 (exactly one head observed), and 2 (heads observed twice).
• Step 4: Compute the probability associated with each outcome. In the provided example,
probabilities can be calculated using the formula: number of favorable outcomes / total
number of possible outcomes.
• Step 5: To formulate the discrete probability distribution, present the probabilities and their
corresponding outcomes in either tabular or graphical format. This process is summarized as
follows:

A histogram can be used to represent the discrete probability distribution for this example.
Example 1: Suppose a pair of fair dice are rolled. Let X be the random variable representing the
sum of the dice. Construct a discrete probability distribution for the same.

Solution: The sample space for rolling 2 dice is given as follows:

Thus, the total number of outcomes is 36.

The possible values of X range between 2 to 12. X = 2 means that the sum of the dice is 2. This can
happen only when (1, 1) is obtained.

Hence, P(X = 2) = 1 / 36.

Using a similar process, the discrete probability distribution can be represented as follows:
 x 2 3 4 5 6 7 8 9 10 11 12
P(X=x) 1 2 3 4 5 6 5 4 3 2 1

The graph of the discrete probability distribution is given as follows

Example 2: Given a discrete probability distribution, find the value of k.

Solution: For a discrete probability distribution, ∑P(X = x) =1.

By using this we get,
0.2 + 0.5 + k + 0.1 = 1
k + 0.8 = 1
k = 1 - 0.8 = 0.2

Example 3: Find the expected value of the given discrete probability distribution.
Solution: The formula for the expected value of a discrete probability distribution is
E[X] = ∑x P(X = x)
E[X] = (0)(0.44) +(1)(0.36) + (2)(0.15) + (3)(0.04) + (4)(0.01)
= 0.82

ACTIVITY 3
Answer the following.
1. Let X be a discrete random variable with the following PMF

a. Find RX, the range of the random variable X

b. Find P(X≤0.5)

c. Find P(0.25<X<0.75)

d. Find P(X=0.2|X<0.6)

REFERENCES
1. Montgomery, D. C. Runger, G. C. Applied Statistics and Probability for Engineers. John Wiley
and Sons. 2011.
2. Triola. M. F. Elementary Statistics. Addison-Wesley. 2012.
3. DeCoursey, W. J. Statistics and Probability for Engineering Applications. Elsevier Science.
2003.