Course contentsShow
← Mathematics
Lesson 3067 of 3,12160. Statistics — ModelingFree lesson

Making Predictions with the Regression Line

Use the fitted regression equation to predict response values for given predictor values.

Making Predictions with the Regression Line

You'll learn: How to use your fitted regression equation to predict unknown response values from new predictor values.

The Core Idea

Once you've calculated the slope and intercept of your least squares regression line (ŷ = b₀ + b₁x), you have a practical prediction tool. Simply plug in any value of your predictor variable (x) into this equation, and out comes your best estimate for the corresponding response variable (y).

Think of the regression line as a mathematical GPS for data: you give it your current location on the x-axis, and it tells you where you should expect to be on the y-axis based on the pattern it learned from your data.

How It Works

Your fitted regression equation looks like:

ŷ = b₀ + b₁x

where:

  • ŷ ("y-hat") is your predicted value
  • b₀ is the intercept you calculated
  • b₁ is the slope you calculated
  • x is the predictor value you're interested in

To make a prediction:

  1. Take your new x-value
  2. Multiply it by the slope (b₁)
  3. Add the intercept (b₀)
  4. The result (ŷ) is your predicted response

Example

Suppose you found that studying hours (x) predicts exam scores (y) with the equation: ŷ = 45 + 8x

If a student studies for 6 hours, your predicted score is: ŷ = 45 + 8(6) = 45 + 48 = 93 points

Important Caution

Only predict within the range of your original data. Extrapolating far beyond invites wild inaccuracies—your regression line only describes the pattern where you actually observed data.

Key Takeaway: The regression line transforms any x-value into a predicted ŷ-value using your fitted equation ŷ = b₀ + b₁x, giving you the single "best guess" based on the linear relationship in your data.