Welcome to the World of the Bell Curve!
In this chapter, we are going to explore one of the most important concepts in all of statistics: the Normal Distribution. You might have heard it called the "Bell Curve" because of its distinctive shape. Whether it’s your height, your examination scores, or even the weight of a bag of chips, many things in the real world follow this pattern. By the end of these notes, you’ll be able to master the math behind these curves and use them to predict probabilities like a pro!
Don’t worry if this seems a bit abstract at first. We’ll take it one step at a time, and soon you'll be seeing normal distributions everywhere!
1. Understanding Continuous Random Variables
Before we dive into the Normal Distribution, we need to understand what a Continuous Random Variable is. Unlike Discrete variables (where you count things like 0, 1, 2, 3), Continuous variables are things you measure.
Think of it this way:
If you count the number of students in a class, that is discrete (you can't have 20.5 students).
If you measure the height of those students, that is continuous (a student could be 170 cm, 170.1 cm, or even 170.154 cm tall).
Key Difference: For continuous variables, the probability of the variable being exactly one specific value is zero \( (P(X = x) = 0) \). Instead, we always look for the probability that a value falls within a range, like \( P(160 < X < 170) \).
Quick Review:
- Discrete: Countable (e.g., number of blue pens).
- Continuous: Measurable (e.g., time taken to run a race).
- We calculate area under a curve to find probabilities for continuous variables.
2. What is a Normal Distribution?
A Normal Distribution is a specific type of continuous probability distribution. We write it as: \( X \sim N(\mu, \sigma^2) \).
There are two "bosses" that control what the curve looks like:
- The Mean (\(\mu\)): This is the center of the curve. It tells you where the peak is located.
- The Variance (\(\sigma^2\)): This tells you how "spread out" the curve is. (Note: \(\sigma\) is the Standard Deviation).
Characteristics of the Normal Curve:
- Symmetrical: The left side is a mirror image of the right side.
- Bell-shaped: It has one peak in the middle.
- The "Trio" are Equal: In a perfect normal distribution, the Mean = Median = Mode.
- Total Area = 1: Because the total probability of any event must equal 100%.
Did you know? Because the curve is symmetrical, exactly 0.5 (or 50%) of the data lies below the mean, and 0.5 lies above the mean!
Key Takeaway: The normal distribution is defined entirely by its mean and variance. If you know these two, you know the whole curve.
3. The Standard Normal Distribution (\(Z\))
Because there are infinite combinations of \(\mu\) and \(\sigma^2\), mathematicians created a "Universal Translator" called the Standard Normal Distribution, denoted by the letter \(Z\).
The Standard Normal Distribution always has:
Mean \((\mu) = 0\)
Variance \((\sigma^2) = 1\)
So, we write it as: \( Z \sim N(0, 1) \).
The Standardization Formula:
To turn any value \(X\) into a \(Z\)-score, we use this formula:
\( Z = \frac{X - \mu}{\sigma} \)
Analogy: Think of \(X\) as a local currency (like Japanese Yen) and \(Z\) as a global currency (like US Dollars). The formula is the "exchange rate" that lets you compare different curves on the same scale.
Memory Aid:
"X marks the spot, subtract the mean, then divide by the spread (SD)."
4. Using your Graphing Calculator (GC)
In the H2 syllabus, you aren't expected to calculate these probabilities by hand. Your GC is your best friend!
A. Finding Probability: normCDF
Use this when you have the values and want the probability (the area).
Syntax: normCDF(lower bound, upper bound, \(\mu\), \(\sigma\))
B. Finding the Value: invNorm
Use this when you are given the probability (area to the left) and need to find the value \(x\).
Syntax: invNorm(area to the left, \(\mu\), \(\sigma\))
Common Mistake to Avoid: Always check if the question gives you Variance (\(\sigma^2\)) or Standard Deviation (\(\sigma\)). The GC requires the Standard Deviation \(\sigma\). If you are given \(\sigma^2 = 16\), you must input \(\sigma = 4\)!
5. Linear Transformations of a Normal Variable
Sometimes, we want to change our variable. For example, if \(X\) is a worker's daily salary, what happens if everyone gets a $10 bonus and their pay is doubled?
If \( X \sim N(\mu, \sigma^2) \), and we create a new variable \( Y = aX + b \):
- New Mean: \( E(aX + b) = aE(X) + b \)
- New Variance: \( Var(aX + b) = a^2Var(X) \)
Wait, why \(a^2\)? Variance measures area/spread. If you double the lengths (\(a=2\)), the area increases by \(2^2 = 4\). Also, notice that adding a constant (\(b\)) does not change the variance. If everyone moves 10 steps to the right, the group is still just as spread out as before!
Key Takeaway: Scaling (\(a\)) affects both mean and variance. Shifting (\(b\)) only affects the mean.
6. Linear Combinations of Independent Variables
What if we add two different independent normal variables together? (e.g., The weight of a box \(X\) and the weight of the fruit inside \(Y\)).
If \( X \sim N(\mu_X, \sigma_X^2) \) and \( Y \sim N(\mu_Y, \sigma_Y^2) \) are independent:
The Mean Rule:
\( E(aX + bY) = aE(X) + bE(Y) \)
The Variance Rule:
\( Var(aX + bY) = a^2Var(X) + b^2Var(Y) \)
CRITICAL POINT: Even if you are subtracting two variables \( (X - Y) \), you ALWAYS ADD the variances!
\( Var(X - Y) = Var(X) + Var(Y) \)
Why? Think of variance as "uncertainty." If you combine two uncertain things, the total uncertainty always grows, whether you are adding or subtracting the actual values.
7. Summary Checklist & Pro-Tips
Before you tackle tutorial questions, keep these tips in mind:
- Check for Independence: You can only add variances if the variables are independent.
- Draw the Curve: When solving probability problems, always sketch a quick bell curve and shade the area you're looking for. It prevents silly mistakes!
- Notation: Be careful with \( N(\mu, \sigma^2) \). In many questions, they write \( N(50, 4) \). Always ask yourself: "Is that 4 the variance or the standard deviation?" (Usually, it's the variance).
- Symmetry: Remember that \( P(X > \mu + k) = P(X < \mu - k) \). Use this to solve tricky problems without a GC.
Great job! You've just covered the essentials of the Normal Distribution. It might feel like a lot of formulas, but with practice, using the GC and the standardization formula will become second nature. Keep going!