# Nakafa Framework: LLM

URL: https://nakafa.com/en/subject/high-school/11/mathematics/statistics/coefficient-of-determination
Source: https://raw.githubusercontent.com/nakafaai/nakafa.com/refs/heads/main/packages/contents/subject/high-school/11/mathematics/statistics/coefficient-of-determination/en.mdx

Output docs content for large language models.

---

import { ScatterDiagram } from "@repo/design-system/components/contents/scatter-diagram";

export const metadata = {
  title: "Coefficient of Determination",
  description: "Learn how r² measures how well your regression line explains data variation. Master coefficient of determination with visual examples and calculations.",
  authors: [{ name: "Nabil Akbarazzima Fatih" }],
  date: "04/30/2025",
  subject: "Statistics",
};

## What is the Coefficient of Determination?

After finding the best-fit linear regression line for our data, the next question is: **how well does that line actually represent or explain our data?**

The measure that answers this question is the **Coefficient of Determination**, denoted as **<InlineMath math="r^2" />** (read: r-squared).

Simply put, <InlineMath math="r^2" /> tells us the **proportion or percentage** of the variation (ups and downs in values) in the dependent variable (Y) that **can be explained** by the variation in the independent variable (X) using our linear regression model.

## Coefficient of Determination from a Scatter Diagram

The value of <InlineMath math="r^2" /> is closely related to how tightly the data points cluster around the regression line:

1. **High <InlineMath math="r^2" /> (approaching 1 or 100%)**

   <ScatterDiagram
     title={
       <>
         High <InlineMath math="r^2" />
       </>
     }
     description="Data points are very close to the regression line."
     xAxisLabel="Variable X"
     yAxisLabel="Variable Y"
     datasets={[
       {
         name: "Data",
         color: "var(--chart-1)",
         points: [
           { x: 1, y: 2 },
           { x: 2, y: 3.1 },
           { x: 3, y: 3.9 },
           { x: 4, y: 5.2 },
           { x: 5, y: 6.1 },
           { x: 6, y: 6.8 },
           { x: 7, y: 8.1 },
           { x: 8, y: 9.0 },
         ],
       },
     ]}
     calculateRegressionLine
     showResiduals
     regressionLineStyle={{ color: "var(--chart-4)" }}
   />

   See how the data points above are very tightly packed and close to the regression line? This indicates a high <InlineMath math="r^2" /> value (for example, maybe around 0.95 or 95%). This means that most of the variation in Y values _can be explained_ well by the regression line (or by variable X).

2. **Low <InlineMath math="r^2" /> (approaching 0 or 0%)**

   <ScatterDiagram
     title={
       <>
         Low <InlineMath math="r^2" />
       </>
     }
     description="Data points are scattered far from the regression line."
     xAxisLabel="Variable X"
     yAxisLabel="Variable Y"
     datasets={[
       {
         name: "Data",
         color: "var(--chart-2)",
         points: [
           { x: 1, y: 1 },
           { x: 2, y: 4 },
           { x: 3, y: 2 },
           { x: 4, y: 6 },
           { x: 5, y: 5 },
           { x: 6, y: 8 },
           { x: 7, y: 6 },
           { x: 8, y: 9 },
         ],
       },
     ]}
     calculateRegressionLine
     showResiduals
     regressionLineStyle={{ color: "var(--chart-4)" }}
   />

   Compare this with this diagram. The points are more spread out from the regression line (the residual lines are longer). This indicates a low <InlineMath math="r^2" /> value (for example, maybe around 0.40 or 40%). This means that this regression line is _not very good_ at explaining the variation in Y values; only a small portion of the variation in Y can be explained by X through this model.

## Calculating the Coefficient of Determination

The easiest way to calculate <InlineMath math="r^2" /> is by **squaring the Correlation Coefficient (<InlineMath math="r" />)** that we learned about earlier.

<BlockMath math="r^2 = (r)^2" />

So, if you've already calculated the value of <InlineMath math="r" />, just square it!

Since the value of <InlineMath math="r" /> is always between -1 and +1 (<InlineMath math="-1 \le r \le 1" />), the value of <InlineMath math="r^2" /> will always be between 0 and 1.

<BlockMath math="0 \le r^2 \le 1" />

**Mathematically (using Sum of Squares):**

The value of <InlineMath math="r^2" /> can also be calculated directly using the Sum of Squares values used to calculate <InlineMath math="r" />:

<BlockMath math="r^2 = \frac{(SS_{xy})^2}{SS_{xx} SS_{yy}}" />

## Interpretation as a Percentage

The value of <InlineMath math="r^2" /> is often converted into a percentage (by multiplying by 100) for easier interpretation.

- If <InlineMath math="r^2 = 0.81" />, it means that **81%** of the total variation in variable Y can be explained by the variation in variable X through the linear regression model.
- The remaining variation (<InlineMath math="1 - r^2" /> or 19% in this example) is explained by other factors not included in the model (could be other variables, or _random error_).

The higher the percentage of <InlineMath math="r^2" />, the better our linear regression model is at explaining the relationship between X and Y.