The Linear Model and Its Parameters
What You'll Learn
You'll learn the components of the simple linear regression equation and what each term represents.
The Core Equation
At the heart of simple linear regression lies this fundamental equation:
y = β₀ + β₁x + ε
Let's break down each piece in plain English:
y (The Response Variable)
This is what you're trying to predict or explain—the outcome. It might be house price, test score, or sales volume.
x (The Predictor Variable)
This is the input you use to make predictions—the variable you believe influences y. Examples: square footage, study hours, or advertising spend.
β₀ (The Intercept)
This is where your line crosses the y-axis when x = 0. It's the baseline value of y before considering the effect of x. Think of it as your starting point.
β₁ (The Slope)
This tells you how much y changes for every one-unit increase in x. If β₁ = 2, then each additional unit of x adds 2 units to y. It captures the strength and direction of the relationship.
ε (The Error Term)
Real data is messy—not every point sits perfectly on a line. The error term captures all the variation in y that your model can't explain with x alone. This includes random noise, measurement error, and the influence of other unmeasured factors.
Analogy
Think of predicting your monthly electricity bill (y) based on temperature (x). β₀ is your baseline usage even when temperature is zero, β₁ tells you how much your bill increases per degree, and ε accounts for those surprise spikes when guests visit.
Key Takeaway: The linear model y = β₀ + β₁x + ε decomposes your outcome into a predictable linear relationship (β₀ + β₁x) plus unexplained variation (ε).