Skip to main content
返回指南
4 min read5 步骤

How to Calculate Linear Regression: Step-by-Step Guide

Learn linear regression calculation by hand

跳过数学——使用计算器

分步说明

1

Gather Your Inputs

First, identify your dataset and calculate the mean of x (x̄) and the mean of y (ȳ), the deviations from the mean for x and y, and the products of the deviations for x and y

2

Calculate the Slope (b1)

Next, plug in the values into the slope formula: b1 = Σ[(xi - x̄)(yi - ȳ)] / Σ(xi - x̄)^2

3

Calculate the Intercept (b0)

Then, use the slope and the means to calculate the intercept: b0 = ȳ - b1 * x̄

4

Calculate the Correlation Coefficient (r)

The correlation coefficient measures the strength of the relationship: r = Σ[(xi - x̄)(yi - ȳ)] / sqrt(Σ(xi - x̄)^2 * Σ(yi - ȳ)^2)

5

Calculate the Residuals

Finally, calculate the residuals by subtracting the predicted values from the actual values: residuals = yi - (b0 + b1 * xi)

Introduction to Linear Regression

Linear regression is a statistical method used to model the relationship between two variables. The goal is to create a linear equation that best predicts the value of one variable based on the value of another variable.

Prerequisites

Before starting, ensure you have a basic understanding of algebra and statistics. You will need a dataset with two variables, x and y.

Step-by-Step Calculation

To calculate the linear regression by hand, follow these steps:

Step 1: Gather Your Inputs

First, identify your dataset and calculate the following:

  • The mean of x (x̄) and the mean of y (ȳ)
  • The deviations from the mean for x and y
  • The products of the deviations for x and y

Step 2: Calculate the Slope (b1)

Next, plug in the values into the slope formula: b1 = Σ[(xi - x̄)(yi - ȳ)] / Σ(xi - x̄)^2

Step 3: Calculate the Intercept (b0)

Then, use the slope and the means to calculate the intercept: b0 = ȳ - b1 * x̄

Step 4: Calculate the Correlation Coefficient (r)

The correlation coefficient measures the strength of the relationship: r = Σ[(xi - x̄)(yi - ȳ)] / sqrt(Σ(xi - x̄)^2 * Σ(yi - ȳ)^2)

Step 5: Calculate the Residuals

Finally, calculate the residuals by subtracting the predicted values from the actual values: residuals = yi - (b0 + b1 * xi)

Worked Example

Suppose we have the following dataset:

x y
1 2
2 3
3 5
4 7
5 8

First, calculate the means: x̄ = 3, ȳ = 5 Then, calculate the deviations and products:

x y x - x̄ y - ȳ (x - x̄)(y - ȳ) (x - x̄)^2
1 2 -2 -3 6 4
2 3 -1 -2 2 1
3 5 0 0 0 0
4 7 1 2 2 1
5 8 2 3 6 4

Now, calculate the slope: b1 = (6 + 2 + 0 + 2 + 6) / (4 + 1 + 0 + 1 + 4) = 16 / 10 = 1.6 Next, calculate the intercept: b0 = 5 - 1.6 * 3 = 5 - 4.8 = 0.2 The correlation coefficient: r = 16 / sqrt(10 * 28) = 16 / sqrt(280) = 16 / 16.73 = 0.96 Finally, calculate the residuals:

x y predicted residual
1 2 2.8 -0.8
2 3 4.4 -1.4
3 5 5.8 -0.8
4 7 7.2 -0.2
5 8 8.6 -0.6

Common Mistakes to Avoid

  • Forgetting to calculate the means of x and y
  • Incorrectly calculating the deviations and products
  • Using the wrong formula for the slope or intercept

When to Use a Calculator

While it's possible to calculate linear regression by hand, it's often more convenient to use a calculator or statistical software, especially for larger datasets. This can save time and reduce the risk of errors.

Conclusion

Linear regression is a powerful tool for modeling the relationship between two variables. By following these steps and using the formulas provided, you can calculate the regression slope, intercept, correlation coefficient, and residuals by hand. However, for larger datasets or more complex analyses, it's often better to use a calculator or statistical software.

准备好计算了吗?

跳过手动工作并立即获得结果。

打开计算器

设置

隐私条款关于© 2026 PrimeCalcPro