01 / 21

Parameters for a
Binomial Distribution

Learn how the parameters \( n \) and \( p \) completely define a binomial distribution and shape every calculation you make.

AP Statistics

What Is a Binomial Setting?

A binomial setting arises whenever you repeat the same chance process multiple times and count the number of successes. Before we can use the binomial model, four conditions must be met:

B
Binary: Each trial has exactly two outcomes: success or failure.
I
Independent: The result of one trial does not affect any other trial.
N
Number: There is a fixed number \( n \) of trials decided in advance.
S
Same probability: The probability \( p \) of success is the same on every trial.

The Two Parameters: \( n \) and \( p \)

A binomial distribution is completely determined by just two numbers. Once you know them, you can compute every probability, the mean, and the standard deviation.

\( n \) : Number of Trials
A fixed, positive integer that tells you how many independent repetitions of the process are performed.
\( p \) : Probability of Success
A value between 0 and 1 (inclusive) that stays constant across every trial in the experiment.

Visualizing How \( n \) and \( p \) Shape the Distribution

\( n = 10, p = 0.5 \)
0 2 4 5 7 9 10 Symmetric
\( n = 10, p = 0.2 \)
0 1 2 3 4 5 6 7 Right-skewed

The Binomial Probability Formula

For a random variable \( X \sim B(n, p) \), the probability of getting exactly \( k \) successes is:

\( \binom{n}{k} \)
The binomial coefficient: the number of ways to choose which \( k \) trials are successes.
\( p^k \)
The probability that all \( k \) chosen trials result in success.
\( (1-p)^{n-k} \)
The probability that the remaining \( n - k \) trials are failures.

Mean and Standard Deviation

Both the center and spread of a binomial distribution are determined entirely by \( n \) and \( p \):

Mean (Expected Value)
\( \mu_X = np \)
The long-run average number of successes over many repetitions.
Standard Deviation
\( \sigma_X = \sqrt{np(1-p)} \)
Measures how much the count of successes typically varies from the mean.

How \( n \) Affects the Distribution

\( n = 5 \)
\( k \)
\( n = 20 \)
\( k \)

Binomial vs. Geometric

Both distributions involve independent trials with the same probability of success, but they count different things:

Binomial Geometric
What it counts Number of successes in \( n \) trials Number of trials until the first success
Parameters \( n \) and \( p \) \( p \) only
Fixed quantity Number of trials (\( n \)) Number of successes (always 1)
Possible values \( 0, 1, 2, \ldots, n \) \( 1, 2, 3, \ldots \) (no upper bound)
Mean \( np \) \( 1/p \)

How to Identify \( n \) and \( p \)

1
Verify BINS. Confirm the setting is Binary, Independent, has a fixed Number of trials, and the Same probability each time.
2
Find \( n \). Look for how many trials, attempts, questions, or items are involved. This is always a positive integer.
3
Find \( p \). Identify the probability of success on a single trial. It may be given as a fraction, decimal, or percentage.
4
Define success. Clearly state what counts as "success" before calculating. The choice of success determines \( p \).
5
Write the model. State \( X \sim B(n, p) \), then use the formula or technology to compute probabilities.

Example 1: Free Throws

A basketball player makes 80% of her free throws. She shoots 10 free throws in a game. Let \( X \) be the number she makes. Find \( P(X = 8) \).

There is about a 30.2% chance she makes exactly 8 out of 10 free throws.

Example 2: Quality Control

A factory produces light bulbs that are defective 3% of the time. An inspector randomly selects 25 bulbs. Find the mean and standard deviation of the number of defective bulbs.

Mean
\( \mu = np = 25 \times 0.03 = \) 0.75 defective bulbs on average.
Standard Deviation
\( \sigma = \sqrt{np(1-p)} = \sqrt{25(0.03)(0.97)} \approx \) 0.853

Example 3: At Least Problems

A multiple-choice quiz has 6 questions, each with 4 choices. A student guesses randomly on every question. What is the probability the student gets at least 2 correct?

There is about a 46.6% chance of getting 2 or more correct by guessing alone.

\( p \) Controls Skewness

\( p = 0.1 \)
Right-skewed
\( p = 0.5 \)
Symmetric
\( p = 0.9 \)
Left-skewed

Normal Approximation Condition

When \( n \) is large enough, the binomial distribution becomes approximately normal. The rule of thumb is:

\( np \geq 10 \)
Ensures there are enough expected successes for the bell shape to emerge on the right side.
\( n(1-p) \geq 10 \)
Ensures enough expected failures so the left side of the distribution also fills out smoothly.

Common Mistakes to Avoid

✕ Swapping \( n \) and \( p \)
Students sometimes write \( B(0.3, 20) \) instead of \( B(20, 0.3) \). Remember: \( n \) always comes first, and it is always a whole number.
✕ Forgetting Independence
Sampling without replacement from a small population violates independence. Use the 10% condition: sample size must be < 10% of the population.
✕ Wrong "Success"
If the question asks about failures (e.g., "how many miss"), either redefine success or use \( q = 1 - p \). Misidentifying success changes every calculation.

Summary of Key Formulas

Property Formula Depends On
Notation \( X \sim B(n, p) \) \( n \) and \( p \)
Probability \( \binom{n}{k} p^k (1-p)^{n-k} \) \( n \), \( p \), and \( k \)
Mean \( \mu = np \) \( n \) and \( p \)
Std. Dev. \( \sigma = \sqrt{np(1-p)} \) \( n \) and \( p \)
Normal approx. \( np \geq 10 \) and \( n(1-p) \geq 10 \) \( n \) and \( p \)

Question 1 of 5

A coin is flipped 15 times. The probability of heads on each flip is 0.5. If \( X \) is the number of heads, what are the parameters of the binomial distribution?

Question 2 of 5

For \( X \sim B(50,\; 0.4) \), what is the mean of \( X \)?

Question 3 of 5

Which of the following is NOT a requirement for a binomial setting?

Question 4 of 5

For \( X \sim B(100,\; 0.3) \), what is the standard deviation of \( X \)?

Question 5 of 5

A binomial distribution with \( n = 40 \) and \( p = 0.1 \) can be well approximated by a normal distribution. True or false?