Multiple regression calculator
Paste an outcome Y and two or three predictor variables. The calculator fits an ordinary least squares model and shows the equation and fit statistics.
Fitted values and residuals
| Row | Y | Ŷ | Residual Y − Ŷ |
|---|---|---|---|
| Fill in the fields above — the result is computed on this page. | |||
How do I use this page?
- Paste Y, X₁ and X₂ in matching row order.
- Optionally add X₃ and press Calculate.
- Read the equation, adjusted R² and RMSE, then inspect residuals.
What this page does not do: The model assumes a linear relationship and independent observations. Strongly correlated predictors can make coefficients unstable. The calculator supports 2 or 3 predictors and up to 200 observations; it does not calculate significance tests or prediction intervals.
Further reading
Theory — what is multiple regression?
Multiple regression describes how one outcome variable Y depends on several predictor variables at once. The coefficient for a given predictor shows how much the predicted Y changes on average when that predictor increases by one unit and the others stay fixed. The model is fitted with ordinary least squares, and fit quality is summarised by R² — for instance, 0.80 means the model explains 80% of Y's variation in the given data. A high R² on historical data is no guarantee of future forecast accuracy.
Frequently asked questions
How do I interpret R²?
What is adjusted R²?
Why are my data rejected?
See also
A/B test calculator
Compare two proportions in an A/B test. Calculate conversion rates, difference, uplift, z score, p value and c
A/B test planning — sample size, MDE and duration
Plan a two-proportion experiment, estimate detectable effect and traffic duration.
ACF and PACF autocorrelation calculator
Calculate ACF and PACF across time-series lags. Review the chart, reference bounds and coefficient table.