In linear regression analysis, a **residual** represents the **difference** between the **actual observed value (y)** of the dependent variable and the **predicted value (ŷ)** generated by the regression model. Residuals, also known as **errors**, illustrate how well the regression line fits the data. A smaller residual indicates a better fit, while a larger residual suggests a less accurate prediction. Understanding residuals is crucial for evaluating the accuracy and reliability of a linear regression model. **Keywords:** linear regression, residual, error, actual value, predicted value, regression line, model fit, accuracy.