Overview
Quadratic regression fits a parabola to your data, for patterns that curve one way, such as a thrown ball or growth that speeds up.
Paste your x-y points, one per line. Add an x value if you want a prediction.
Worked examples
| Inputs | Result |
|---|---|
| Your x-y points1, 2.1 · 2, 3.9 · 3, 9.2 · 4, 15.8 · 5, 25.3 · 6, 35.9 | y = 1.0857x² − 0.74857x + 1.52R²: 0.9994 from 6 points |
How it works
The curve is chosen by least squares, which makes the squared vertical distances from the points to the curve as small as possible. R² shows the share of the variation in y the curve explains.
The formula
| a | Curvature: positive opens up, negative opens down |
| b, c | Set the position of the curve |
Practical tips
- You need at least three points with different x values.
- Parabolas shoot off quickly outside your data, so treat predictions beyond it with care.
- If a straight line fits nearly as well, the simpler line is usually the better choice.
Frequently asked questions
When should I use quadratic instead of linear regression?
When the chart shows a clear single bend that a straight line misses.
What does a negative a mean?
The parabola opens downward, so y rises to a peak and then falls.
Why is R² so high with few points?
Three points always fit a parabola exactly, so add more points for a meaningful R².