Welcome to the Normal Distribution!
In this chapter, we are going to explore one of the most important concepts in all of statistics. The Normal Distribution is often called the "Bell Curve" because of its shape. Don't worry if this seems tricky at first; it is actually a very logical way to look at how data behaves in the real world!
We use the Normal Distribution to describe things that happen naturally, like the heights of people, the weight of apples in a shop, or even your exam scores. Most things are "average," with fewer things being very small or very large. That is exactly what this curve shows us.
1. What is a Normal Distribution?
Imagine you measured the height of every student in your school. You would find that most students are around the same average height. A few are very tall, and a few are very short, but most cluster in the middle. This "clustering" creates a symmetrical shape called the Normal Curve.
Key Properties to Remember:
• It is symmetrical: The left side is a mirror image of the right side.
• The mean (\(\mu\)), median, and mode are all at the exact center.
• The total area under the curve is always 1 (this represents a total probability of 100%).
• It never quite touches the horizontal axis; it goes on forever in both directions!
Quick Review:
A Normal Distribution is defined by two numbers:
1. The Mean (\(\mu\)): This tells you where the center of the curve is.
2. The Standard Deviation (\(\sigma\)): This tells you how "spread out" the curve is. A big \(\sigma\) means a wide, flat curve. A small \(\sigma\) means a tall, thin curve.
2. The Standard Normal Distribution (\(Z\))
Because there are millions of possible combinations of means and standard deviations, mathematicians created a "Universal Translator" called the Standard Normal Distribution. We use the letter \(Z\) to represent this.
In the \(Z\) distribution:
• The mean \(\mu = 0\)
• The standard deviation \(\sigma = 1\)
How to Standardize (The \(Z\)-score formula)
To turn any value \(X\) into a \(Z\)-score, we use this formula:
\( Z = \frac{X - \mu}{\sigma} \)
Analogy: Think of \(Z\) as a "Universal Currency." If you have 100 Yen and your friend has 5 Dollars, you need to convert them to a standard currency to see who has more. Standardizing turns your data into "standard units" so you can use the probability tables.
3. Finding Probabilities
When a question asks for a probability, it is asking for the area under the curve. Your calculator or your formula booklet tables usually give you the area to the left of a value (\(P(X < a)\)).
Step-by-Step: Solving a Problem
Example: A type of battery lasts an average of 50 hours (\(\mu = 50\)) with a standard deviation of 5 hours (\(\sigma = 5\)). What is the probability a battery lasts less than 42 hours?
Step 1: Write down what you know.
\(X \sim N(50, 5^2)\). We want to find \(P(X < 42)\).
Step 2: Standardize to find \(Z\).
\(Z = \frac{42 - 50}{5} = \frac{-8}{5} = -1.6\)
Step 3: Draw a quick sketch!
Draw a bell curve, mark the middle as 0, and shade the area to the left of -1.6. This helps you see if your answer should be big or small.
Step 4: Use your table or calculator.
Looking up \(Z = -1.6\) gives a probability of approximately 0.0548.
Common Mistake to Avoid:
The tables often give the area to the left. If the question asks for "greater than" (\(P(X > a)\)), you must calculate: \(1 - \text{Table Value}\).
4. The Inverse Normal (Working Backward)
Sometimes, the question gives you the probability (the area) and asks you to find the original value (\(x\)). This is called the Inverse Normal.
Memory Aid: "Inside-Out"
Normal Probability = \(X \rightarrow Z \rightarrow \text{Area}\)
Inverse Normal = \(\text{Area} \rightarrow Z \rightarrow X\)
To find \(X\) from \(Z\), we rearrange our formula:
\( X = \mu + (Z \times \sigma) \)
Quick Review Box:
• If the area is less than 0.5, your \(Z\)-score will be negative.
• If the area is more than 0.5, your \(Z\)-score will be positive.
5. Approximating a Binomial Distribution
(Check your specific exam requirements, as this is often a key part of the S1 syllabus!)
If you have a Binomial Distribution with a large number of trials (\(n\)) and the probability (\(p\)) is close to 0.5, the shape starts to look exactly like a Normal Distribution. We can use the Normal Distribution to make calculations easier!
When can you use this?
You can use the approximation if:
1. \(np > 5\)
2. \(n(1-p) > 5\)
How to do it:
• Use Mean \(\mu = np\)
• Use Variance \(\sigma^2 = np(1-p)\)
Important Trick: Continuity Correction
Because Binomial data is discrete (whole numbers) and Normal data is continuous (any decimal), we have to adjust. If you want to find \(P(X \ge 10)\) in Binomial, you use \(P(X > 9.5)\) in the Normal approximation. Always go 0.5 units below or above the number!
6. Summary Key Takeaways
• The Parameters: \(\mu\) is the center, \(\sigma\) is the spread.
• Standardizing: Use \( Z = \frac{X - \mu}{\sigma} \) to move from real-world data to the \(Z\)-table.
• Symmetry: Use the symmetry of the curve to find areas on the negative side if your table only shows positive values.
• Sketching: Always draw a small curve and shade the area. It is the best way to prevent simple mistakes!
• Probabilities: The total area is 1. If you need the right side, subtract the left side from 1.
Did you know?
The Normal Distribution was discovered by Carl Friedrich Gauss. This is why it is sometimes called the Gaussian Distribution. He used it to predict the location of planets and stars!