The Binomial Distribution as a Model

Welcome to your study guide on the Binomial Distribution! Don't worry if probability sometimes feels tricky or confusing. In this chapter, we will break everything down into bite-sized, easy-to-follow steps. By the end of these notes, you will know exactly when to use this model, how to write its notation, and how to calculate probabilities and expected values with confidence.

Did you know? The prefix "bi-" means two (just like a bicycle has two wheels or binoculars have two lenses). The binomial distribution is all about situations where there are only two possible outcomes for every trial: success or failure!

1. When Can We Use a Binomial Model?

In real life, we often repeat an action multiple times and count how many times a specific event occurs. For example, flipping a coin \(10\) times and counting the number of heads, or rolling a dice \(5\) times and counting how many sixes you get.

To use a binomial distribution as a mathematical model, the situation must meet four strict conditions. You can easily remember them using the handy mnemonic BINS:

B – Binary outcomes: There are only two possible outcomes for each trial. We label these as Success and Failure.
Example: Passing a driving test (Success) or failing (Failure); rolling a \(6\) (Success) or not rolling a \(6\) (Failure).

I – Independent trials: The outcome of one trial has no effect on the outcome of any other trial.
Example: Flipping a 'Tails' on your first coin toss does not change the chance of getting 'Heads' on your second coin toss.

N – Number of trials is fixed: The experiment is repeated a set number of times, denoted by the letter \(n\). You decide the number of trials in advance, rather than repeating until something happens.
Example: Exactly \(n = 10\) penalty kicks.

S – Same probability of success: The probability of success, denoted by \(p\), must stay constant for every single trial.
Example: The chance of guessing a multiple-choice question correctly with \(4\) options is always \(p = 0.25\) on every question.

Quick Review: The BINS Checklist

Whenever an exam question asks: "State the assumptions needed to model this situation using a binomial distribution," just write down the BINS criteria using the context of the question!

Key Takeaway: If a situation has a fixed number of trials, two outcomes per trial, independent trials, and a constant probability, we can model it using the binomial distribution.

2. Binomial Notation

Statisticians use a shorthand notation so they don't have to write long sentences every time. If a random variable \(X\) follows a binomial distribution, we write:

\(X \sim \text{B}(n, p)\)

Let's unpack what each symbol means:

• \(X\) represents the random variable (the count of successes we are interested in).
• \(\sim\) means "is distributed as" or "follows the model of".
• \(\text{B}\) stands for Binomial.
• \(n\) is the number of trials.
• \(p\) is the probability of success in a single trial.

Analogy Time:

Think of \(n\) and \(p\) as the "ingredients" or parameters of the recipe. Once you know how many attempts you have (\(n\)) and how likely each attempt is to succeed (\(p\)), the entire probability distribution is fixed!

Key Takeaway: Always identify \(n\) and \(p\) first when reading any binomial exam question.

3. Calculating Probabilities: The Formula

Suppose you throw a fair dice \(5\) times. What is the probability of getting exactly \(2\) sixes? We can calculate the probability of getting exactly \(r\) successes using the binomial probability formula:

\(P(X = r) = \binom{n}{r} \times p^r \times (1 - p)^{n - r}\)

Sometimes the failure probability is written as \(q\), where \(q = 1 - p\). So the formula can also be written as:

\(P(X = r) = \binom{n}{r} p^r q^{n - r}\)   or   \(P(X = r) = {^n\text{C}_r} \times p^r \times q^{n - r}\)

Understanding the Three Parts of the Formula:

1. \(\binom{n}{r}\) or \({^n\text{C}_r}\) (The Combinations part): This tells us the number of different arrangements/orders in which the \(r\) successes can occur across the \(n\) trials. You can find this on your calculator using the nCr button.
2. \(p^r\) (The Success part): The probability of success multiplied by itself \(r\) times for the \(r\) successes.
3. \((1 - p)^{n - r}\) (The Failure part): The probability of failure multiplied by itself for the remaining \((n - r)\) trials.

Step-by-Step Worked Example:

Question: A fair coin is tossed \(6\) times. Find the probability of getting exactly \(4\) Heads.

Step 1: Identify the parameters.
Number of trials: \(n = 6\)
Success: Getting a Head, so \(p = 0.5\)
Failure: Getting a Tail, so \(q = 1 - 0.5 = 0.5\)
Number of successes wanted: \(r = 4\)

Step 2: Write down the formula with values inserted.
\(P(X = 4) = \binom{6}{4} \times (0.5)^4 \times (0.5)^{6 - 4}\)

Step 3: Calculate each part.
\(\binom{6}{4} = 15\)
\((0.5)^4 = 0.0625\)
\((0.5)^2 = 0.25\)

Step 4: Multiply them together.
\(P(X = 4) = 15 \times 0.0625 \times 0.25 = 0.234375\) (or \(0.234\) to \(3\) decimal places).

Key Takeaway: The binomial formula is just (ways to arrange) \(\times\) (chance of successes) \(\times\) (chance of failures).

4. Cumulative Probabilities ("At least", "At most", "Fewer than")

Exam questions often ask for a range of outcomes rather than just a single exact number. Translating everyday English words into correct mathematical symbols is a crucial skill!

Translating the Language of Inequalities:

• "At most \(2\)" or "No more than \(2\)" means: \(P(X \le 2) = P(X = 0) + P(X = 1) + P(X = 2)\)
• "Fewer than \(2\)" or "Less than \(2\)" means: \(P(X < 2) = P(X = 0) + P(X = 1)\)
• "At least \(1\)" means: \(P(X \ge 1)\). A super fast shortcut is to use the complement rule: \(P(X \ge 1) = 1 - P(X = 0)\)
• "More than \(2\)" means: \(P(X > 2) = 1 - P(X \le 2)\)

Helpful Shortcut for "At Least One":

The phrase "at least one success" comes up very often! Instead of calculating \(P(X = 1) + P(X = 2) + \dots + P(X = n)\), simply find the probability of zero successes and subtract it from \(1\):

\(P(X \ge 1) = 1 - P(X = 0)\)

Key Takeaway: Always list out the numbers included in the inequality before calculating so you don't accidentally add the wrong probabilities!

5. Mean (Expected Value) of a Binomial Distribution

The mean (also called the expected value, written as \(\text{E}(X)\) or \(\mu\)) tells us the average number of successes we would expect if we repeated the experiment many times.

The Formula for the Mean:

\(\text{Mean} = \mu = n \times p\)

This formula makes complete intuitive sense! For instance, if you roll a fair dice \(60\) times, and the probability of rolling a six is \(p = \frac{1}{6}\), how many sixes would you expect to get?

\(\text{Mean} = 60 \times \frac{1}{6} = 10\text{ sixes}\)

Example: A student sits a multiple choice test with \(20\) questions. Each question has \(5\) options, so the probability of randomly guessing correctly is \(p = \frac{1}{5} = 0.2\).
The expected score from pure guessing is:
\(\text{Mean} = n \times p = 20 \times 0.2 = 4\text{ correct answers}\).

Key Takeaway: To find the average/expected number of successes, simply multiply the number of trials \(n\) by the probability of success \(p\).

6. Common Mistakes to Avoid

Keep these frequent traps in mind when revising:

Mistake 1: Forgetting the combinations factor \(\binom{n}{r}\).
Students sometimes write \(p^r (1-p)^{n-r}\) and forget to multiply by \(\binom{n}{r}\). Unless \(r = 0\) or \(r = n\), there is more than one order in which successes can happen!

Mistake 2: Confusing "at least" with "more than".
"At least \(3\)" includes \(3\) (\(X \ge 3\)), whereas "more than \(3\)" starts at \(4\) (\(X > 3\)).

Mistake 3: Using a binomial model when trials are not independent.
If you are picking items without replacement from a small group (e.g. picking \(3\) red socks from a drawer containing \(5\) red and \(5\) blue socks), the probability changes after each pick. A binomial model is not valid here because the trials are not independent and \(p\) is not constant!

Summary Checklist

Before sitting your exam, ensure you can:

1. State the 4 conditions needed for a binomial model (BINS).
2. State the parameters \(n\) and \(p\) and write the model as \(X \sim \text{B}(n, p)\).
3. Use the formula \(P(X = r) = \binom{n}{r} p^r (1 - p)^{n - r}\) accurately on your calculator.
4. Work out cumulative probabilities like \(P(X \le r)\) and use the shortcut \(P(X \ge 1) = 1 - P(X = 0)\).
5. Calculate the expected value using \(\text{Mean} = n p\).