Linear Regression Slope Calculator Formula

Understand the math behind the linear regression slope calculator. Each variable explained with a worked example.

Formulas Used

Slope (b1)

slope = (n * sum_xy - sum_x * sum_y) / (n * sum_x2 - pow(sum_x, 2))

Variables

VariableDescriptionDefault
nNumber of Data Points (n)10
sum_xySum of x*y (Σxy)3500
sum_xSum of x (Σx)150
sum_ySum of y (Σy)200
sum_x2Sum of x² (Σx²)2850

How It Works

Linear Regression Slope

The slope of the least-squares regression line measures the average change in y for each one-unit increase in x.

Formula

b1 = (n × Σxy - Σx × Σy) / (n × Σx² - (Σx)²)

This is derived by minimizing the sum of squared residuals. A positive slope indicates a positive relationship; negative slope indicates an inverse relationship.

Worked Example

Given n=10, Σxy=3500, Σx=150, Σy=200, Σx²=2850.

n = 10sum_xy = 3500sum_x = 150sum_y = 200sum_x2 = 2850
  1. 01Numerator = 10(3500) - 150(200) = 35000 - 30000 = 5000
  2. 02Denominator = 10(2850) - 150² = 28500 - 22500 = 6000
  3. 03b1 = 5000 / 6000 = 0.8333

Frequently Asked Questions

What does the slope represent?

The slope b1 represents the predicted change in the response variable y for a one-unit increase in the predictor x. It quantifies the strength and direction of the linear relationship.

Can the slope be zero?

Yes. A slope of zero means there is no linear relationship between x and y. This is tested with a t-test where t = b1 / SE(b1). If t is not significant, the slope is not distinguishable from zero.

How does sample size affect the slope estimate?

Larger samples give more precise slope estimates (smaller standard error). The slope itself does not systematically change with sample size, but confidence intervals narrow.