Math

Linear Regression Calculator

Fit a best-fit line from point data and compute r and R².

Last validated: 2026-02-14

Linear Regression Calculator fits a best-fit line and returns slope/intercept from paired data. It is useful for trend estimation and quick predictive checks in small datasets. The tool helps confirm whether a linear model is reasonable before deeper analysis. Use it to inspect relationship direction and strength.

Permalink

Input Pattern

Enter values in the left panel, keep units explicit, run the calculation, then copy or share the result. Invalid fields are highlighted immediately.

Point Data

One point per line: `x,y`

Model

Line: y = 0.900000x + 1.300000

r: 0.900000

R²: 0.810000

Points used: 5

How to use this tool

Enter x-y data pairs in the expected format.
Run regression to compute slope, intercept, and fit metrics.
Use coefficients for forecasting or model comparison.

Worked Example

Auto-generated from the tool's current default or entered inputs.

Example Inputs

Slope: 0.9
Intercept: 1.3
R value: 0.9
R squared: 0.81

Expected Outputs

Parsed points 0 0: 1
Parsed points 0 1: 2
Parsed points 1 0: 2
Parsed points 1 1: 3

Interpretation

Parsed points 0 0 is 1.0. Use this as a decision input, not as a standalone conclusion.
Parsed points 0 1 is 2.0. Use this as a decision input, not as a standalone conclusion.
Parsed points 1 0 is 2.0. Use this as a decision input, not as a standalone conclusion.
Interpret this value alongside sample quality and assumptions to avoid overconfidence.

Scenario Compare (A vs B)

Use this to compare two input sets and quantify change in key outputs.

Confidence and limitations

Outputs are deterministic formula results and depend entirely on input quality and units.
Results are for planning and learning; verify with domain standards before safety-critical use.
Rounding and finite precision can introduce small differences in edge cases.

Formula References

Algebra and arithmetic identities used by the selected formula.
Standard precision arithmetic; rounding shown for readability.

Assumptions

Outputs are deterministic formula results and depend entirely on input quality and units.
Results are for planning and learning; verify with domain standards before safety-critical use.
Rounding and finite precision can introduce small differences in edge cases.

Explore more versions

Tailored guides for specific audiences, regions, and scenarios.

core