Binomial distribution
The binomial probability distribution is a discrete distribution that has many
applications. It is associated with a multi-step experiment called a binomial experiment.
The word binomial comes from another word that means "two names" and this will
remind us that in each essay that we will see in this topic there will always be two results:
success and failure. If you answer a question of random alternatives, the answer is
correct or incorrect. If you perform a quality control on a product, it will be defective or
not defective. If you flip a coin, it comes up heads or tails. Let's see in detail the binomial
distribution, its formula.
Binomial experiment
A binomial experiment is an experiment that satisfies the 4 following conditions:
1. The experiment consists of a sequence of n identical trials.
2. On each trial there are two possible outcomes. One of them is called
success and the other, failure.
3. The probability of success is constant from trial to trial, never changes, and is denoted by p.
Therefore, the probability of failure will be 1 – p. This is because the probability of success plus
the probability of failure add up to 1.
4. The trials are independent, so the result of any one of them does not influence the result of
any other trial.
Before solving an exercise applying the binomial probability formula, we always have to verify
that these four conditions are met, since this formula only works for binomial experiments.
This is already getting very boring, better let's see an example.
Experiment 1
George's Burgers
________________________________________
The probability that a new customer likes a burger is 0.8. If 3 new customers come to the
cafeteria, what is the probability that only two of them will like the hamburger?
If the customer likes the hamburger, will have a happy face and if he does not like it, he will
have an angry face. For example, if the first two like it and the third does not, the graph placed
for that is the follwing:
But it is not the only option, in total there are three options. The first two like it and the third
doesn't. That the first and the third like it, and the second not. Or that the second and third
like it and the first doesn't. We graph these three options:
If the probability that a customer likes the burger is 0.8, then the probability that they don't
like it is:
We will now calculate the probability of each event occurring. For example, in the first line,
we'll compute the probability that the first and second customers like the hamburger and the
third doesn't. We will apply the rule of multiplication of probabilities for independent events.
Now, putting all the options.
These same probabilities, can be placed in the form of powers:
just keeping the powers and eliminating the rest.
Next, we calculate the total probability that only 2 of the 3 customers like the burger using the
rule of the sum of probabilities for mutually exclusive events.
If we put this multiplication into the calculator, we would have 0.384 as a result.
Is this calculation a bit long? Yes, it is very long. Imagine that now 10 new customers arrive at
the cafeteria and we want to calculate the probability that 4 of them like the burger. It would
take hours, so it's better to use the binomial probability function formula. This formula allows
us to find the probability for each possible value of x (number of successes).
Binomial probability function (formula)
________________________________________
For a binomial experiment, let p be the probability of “success” and 1-p be the probability of a
“failure” on a single trial; then the probability of getting x successes in n trials is given by the
probability function f(x):
Being the binomial coefficient or combinatorial number:
For this reason, in some books you will find the binomial probability function f(x) with the
binomial coefficient already incorporated and presented as follows:
Which of the ways is the best? That already depends on what your heart says, but remember
that the result is the same.
The binomial probability function applies to any binomial experiment. If a situation
demonstrates the properties of a binomial experiment and the values of n and p are known,
the above equation can be used to calculate the probability of x successes in n trials.
The probability that a new customer likes George's burger is 0.8. If 5 new customers come to
the cafeteria, what is the probability that only 3 of them like the burger?
Solution:
Before applying the formula, we verify that it is a binomial experiment. For this, you have to
meet the 4 conditions that we mentioned above. Indeed, it is a binomial experiment.
In this case, we are going to focus on the customers who like this burger, so we will say that:
X = number of new customers out of 5 who like the burger
So we consider it a success if the customer likes this burger.
We will apply the binomial formula:
Now we put the values of n, x and p. Remember that n is the number of trials, x the number of
successes, and p the probability of success.
n=5
x=3
p = 0.8
We substitute these values into the formula:
Example 2
________________________________________
Of all the flowers planted by a garden company, 90% survive. If 10 flowers are planted, what is
the probability that 9 or more will survive?
Solution:
Before applying the formula, we verify that it is a binomial experiment. For this, you have to
meet the 4 conditions that we mentioned above. Indeed, it is a binomial experiment.
In this case, we are going to focus on the flowers that survive, so we will say that:
X = number of flowers out of 10 that survive
So we consider a success if the flower survives. Those flowers that die, we consider as a failure.
We will apply the binomial formula:
We are asked to calculate the probability that 9 or more survive.
This problem is tricky, because up to 10 flowers have been planted, the maximum number of
flowers that can survive is 10, therefore:
– And can't 11 flowers survive?
– It is not possible, because only 10 were planted.
Now we put the values of n, and p. Remember that n is the number of trials, x the number of
successes, and p the probability of success. In this case:
We return with the formula above:
Let's calculate each probability separately, starting with P(X = 9):
We continue with P(X = 10).
We return with this formula:
And we replace the calculated:
That would be the answer: 0.64 or 64%
Conclusion: the probability of getting at least 1 success 64%
