Regression & Scatter Plot

Fit a line or curve to data using least squares. See R², correlation coefficient, and residuals update in real time. Drag points to explore how data shape affects the fit.

Regression

Drag points to change the data

Properties

n (points)--
Equation--
Slope--
Intercept--
--
r--

The Math Behind It

Least Squares

  • Goal: minimize the sum of squared residuals — Σ(yi − ŷi
  • Slope: m = Σ(xi − x̄)(yi − ȳ) / Σ(xi − x̄)²
  • Intercept: b = ȳ − m·x̄
  • The least squares line passes through (x̄, ȳ)
  • Quadratic fit solves a 3×3 normal equation system

Goodness of Fit

  • = 1 − SSres/SStot — proportion of variance explained
  • R² = 1 means a perfect fit; R² = 0 means no linear relationship
  • Correlation coefficient: r = ±√R² — sign matches the slope
  • Residual = observed − predicted — vertical distance from point to line
  • Residuals should be randomly scattered for a good fit