simpleLinearRegression

Fits a simple linear regression model (y = intercept + slope * x) using ordinary least squares.

Simple linear regression finds the straight line that best fits the data by minimizing the sum of squared residuals (differences between observed and predicted y values). The result includes the fitted coefficients, goodness-of-fit measure (R²), standard errors, and residuals.

Example:

val x = doubleArrayOf(1.0, 2.0, 3.0, 4.0, 5.0)
val y = doubleArrayOf(3.0, 5.0, 7.0, 9.0, 11.0)
val result = simpleLinearRegression(x, y)
result.slope     // 2.0
result.intercept // 1.0
result.rSquared  // 1.0 (perfect fit)
result.predict(6.0) // 13.0

Note on numerical precision: the intercept is computed as meanY - slope * meanX. For data with a large constant offset (e.g. values around 1e12), this subtraction of nearly equal numbers may lose significant digits in the intercept estimate. The slope and R² are not affected.

Parameters

Throws