Welcome to Combinations of Random Variables!
In this chapter, we are going to explore what happens when we mix and match different random variables. Think of it like a recipe: if you know the nutritional value of one apple and one orange, how do you calculate the total for a fruit salad? In Further Statistics 2, we specifically focus on independent Normal random variables. By the end of these notes, you’ll be able to predict the "average" and the "spread" of these combinations with ease.
Don't worry if this seems a bit abstract at first—once you see the patterns, it’s just like following a simple set of rules!
1. The Golden Rule: Independence
Before we touch any formulas, we must talk about Independence. Two random variables, \( X \) and \( Y \), are independent if the outcome of one has absolutely no effect on the outcome of the other.
Example: If you measure the height of a randomly selected student in London (\( X \)) and the weight of a randomly selected cat in Tokyo (\( Y \)), these are independent. However, the height and weight of the same person are usually not independent.
Key Takeaway: For the formulas in this chapter to work, the variables must be independent. The exam will usually state this, but it’s a vital "check" to have in your mind!
2. Combining the Averages (Expectation)
When we combine variables, the Expectation (the mean or average) behaves exactly how you would expect it to. It follows linear rules.
If we have a combination like \( aX + bY \), where \( a \) and \( b \) are just numbers (constants), the new mean is:
\( E(aX + bY) = aE(X) + bE(Y) \)
If we are subtracting them:
\( E(aX - bY) = aE(X) - bE(Y) \)
Analogy: If a box of cereal averages 500g and a bottle of milk averages 1000g, then the total average weight of 2 boxes and 3 bottles is simply \( (2 \times 500) + (3 \times 1000) = 4000g \). Simple, right?
3. Combining the Spread (Variance)
This is where things get interesting—and where students often make mistakes! Variance does not behave quite like the mean. There are two "Golden Tricks" to remember for variance:
Trick 1: The Square Rule
When you multiply a variable by a constant \( a \), the variance is multiplied by \( a^2 \).
\( Var(aX) = a^2Var(X) \)
Trick 2: Variances Always Add
Even if you are subtracting two variables, their variances still add up. This is because combining two uncertain things always results in more total uncertainty, never less.
\( Var(aX \pm bY) = a^2Var(X) + b^2Var(Y) \)
Common Mistake Alert! Never subtract variances. If you see a minus sign in the combination (e.g., \( X - Y \)), the variance formula still uses a plus sign! Think of it this way: if you are comparing two heights, the "gap" between them is also a random variable, and that gap is just as "wobbly" and uncertain as the heights themselves.
4. The Normal Distribution Combination
According to the Pearson Edexcel Syllabus (Section 4.1), if your individual variables follow a Normal Distribution, their combination will also follow a Normal Distribution. This is a very powerful tool!
If:
\( X \sim N(\mu_x, \sigma_x^2) \)
\( Y \sim N(\mu_y, \sigma_y^2) \)
Then for any constants \( a \) and \( b \):
\( aX \pm bY \sim N(a\mu_x \pm b\mu_y, a^2\sigma_x^2 + b^2\sigma_y^2) \)
Step-by-Step Process for Problems:
1. Identify the means (\( \mu \)) and variances (\( \sigma^2 \)) for each variable.
2. Calculate the new combined mean using the linear rule.
3. Calculate the new combined variance (remember to square constants and always add).
4. Write down the new distribution in the form \( \sim N(\text{new mean}, \text{new variance}) \).
5. Use your calculator to find probabilities as you normally would!
5. Difference Between \( 2X \) and \( X_1 + X_2 \)
This is a classic exam "trap." It is very important to read the question carefully to see if you are looking at one item scaled up, or multiple different items.
Case A: \( 2X \) (One item doubled)
Imagine one giant chocolate bar that is exactly twice the size of a standard one.
\( E(2X) = 2E(X) \)
\( Var(2X) = 2^2Var(X) = 4Var(X) \)
Case B: \( X_1 + X_2 \) (Two independent items)
Imagine two separate standard chocolate bars.
\( E(X_1 + X_2) = E(X) + E(X) = 2E(X) \)
\( Var(X_1 + X_2) = Var(X) + Var(X) = 2Var(X) \)
Did you know? The variance of two separate items is smaller than the variance of one item doubled. This is because, with two items, an unusually heavy one might be cancelled out by an unusually light one. With one item doubled, if it's heavy, the whole thing is "double-heavy"!
Quick Review Box
Means: Follow the signs. If it's \( + \), add. If it's \( - \), subtract.
Variances: 1. Square the coefficients. 2. Always add the results.
Distribution: Normal + Normal = Normal (provided they are independent).
Check: Did the question give you Standard Deviation (\( \sigma \)) or Variance (\( \sigma^2 \))? Always square the Standard Deviation before putting it into the combination formula!
Summary Takeaway
The core of this chapter is the formula: \( aX \pm bY \sim N(a\mu_x \pm b\mu_y, a^2\sigma_x^2 + b^2\sigma_y^2) \). Master this, and you have mastered the chapter. Just remember that variance is always "additive" when independent variables are combined, and you'll avoid the most common pitfall in Further Statistics 2!