# Nakafa Framework: LLM

URL: /en/subject/high-school/10/mathematics/statistics/variance-standard-deviation-data-single
Source: https://raw.githubusercontent.com/nakafaai/nakafa.com/refs/heads/main/packages/contents/subject/high-school/10/mathematics/statistics/variance-standard-deviation-data-single/en.mdx

Output docs content for large language models.

---

export const metadata = {
  title: "Variance and Standard Deviation for Ungrouped Data",
  description: "Master variance and standard deviation calculations for ungrouped data with clear formulas and real examples. Analyze data spread effectively.",
  authors: [{ name: "Nabil Akbarazzima Fatih" }],
  date: "04/22/2025",
  subject: "Statistics",
};

## Measuring Spread with Variance and Standard Deviation

There's a powerful way to measure how spread out our data is: **Variance** and **Standard Deviation**.

These two measures tell us how far, on average, each data point deviates from the group's **mean** (average).

- If the **Variance** or **Standard Deviation** value is **small**, it means the data points in the group tend to be **uniform** or **similar**, clustering **close** to the mean value.
- If the value is **large**, it means the data points are more **varied** or **diverse**, spreading **further away** from the mean value.

## Formulas for Variance and Standard Deviation

1.  **Variance (<InlineMath math="\sigma^2" />)**

    Variance is the average of the squared differences of each data point from the mean. Confused? Simply put: calculate the difference between each data point and the mean, square the result, then average those squared differences.

    The formula is:

    <BlockMath math="\sigma^2 = \frac{\sum_{i=1}^{n}(x_i - \bar{x})^2}{n}" />

    Where:

    - <InlineMath math="\sigma^2" /> = Variance
    - <InlineMath math="x_i" /> = Value of the i-th data point
    - <InlineMath math="\bar{x}" /> = Mean (average) of the data
    - <InlineMath math="n" /> = Number of data points
    - <InlineMath math="\sum" /> = Sum all the calculated results

2.  **Standard Deviation (<InlineMath math="\sigma" />)**

    Standard deviation is more commonly used because its unit is the same as the original data unit (variance has squared units). It's simple: just take the square root of the variance.

    The formula is:

    <BlockMath math="\sigma = \sqrt{\sigma^2} = \sqrt{\frac{\sum_{i=1}^{n}(x_i - \bar{x})^2}{n}}" />

## Comparing Variance in Two Age Groups

Let's use an example of two groups of age data to see how variance and standard deviation work. These groups are interesting because they have the **same mean (<InlineMath math="\bar{x}" />), which is 16**, but their data spreads are different.

- **Group One (<InlineMath math="n=12" />):** 13, 14, 15, 15, 16, 16, 17, 17, 17, 17, 17, 18
- **Group Two (<InlineMath math="n=12" />):** 1, 3, 4, 5, 7, 8, 12, 27, 28, 29, 32, 36

Now, let's calculate the Variance and Standard Deviation for each group.

### Calculation for Group 1

We calculate <InlineMath math="(x_i - \bar{x})^2" /> for each data point in Group 1 (<InlineMath math="\bar{x}=16" />):

- <InlineMath math="(13-16)^2 = (-3)^2 = 9" />
- <InlineMath math="(14-16)^2 = (-2)^2 = 4" />
- <InlineMath math="(15-16)^2 = (-1)^2 = 1" /> (2 data points)
- <InlineMath math="(16-16)^2 = (0)^2 = 0" /> (2 data points)
- <InlineMath math="(17-16)^2 = (1)^2 = 1" /> (5 data points)
- <InlineMath math="(18-16)^2 = (2)^2 = 4" />

Now sum all these squared results (<InlineMath math="\sum(x_i - \bar{x})^2" />):

<BlockMath math="9 + 4 + (1 \times 2) + (0 \times 2) + (1 \times 5) + 4 = 9 + 4 + 2 + 0 + 5 + 4 = 24" />

Calculate the Variance:

<BlockMath math="\sigma^2_{\text{Group 1}} = \frac{\sum(x_i - \bar{x})^2}{n} = \frac{24}{12} = 2" />

Calculate the Standard Deviation:

<BlockMath math="\sigma_{\text{Group 1}} = \sqrt{2} \approx 1.41" />

### Calculation for Group 2

We calculate <InlineMath math="(x_i - \bar{x})^2" /> for each data point in Group 2 (<InlineMath math="\bar{x}=16" />):

- <InlineMath math="(1-16)^2 = (-15)^2 = 225" />
- <InlineMath math="(3-16)^2 = (-13)^2 = 169" />
- <InlineMath math="(4-16)^2 = (-12)^2 = 144" />
- <InlineMath math="(5-16)^2 = (-11)^2 = 121" />
- <InlineMath math="(7-16)^2 = (-9)^2 = 81" />
- <InlineMath math="(8-16)^2 = (-8)^2 = 64" />
- <InlineMath math="(12-16)^2 = (-4)^2 = 16" />
- <InlineMath math="(27-16)^2 = (11)^2 = 121" />
- <InlineMath math="(28-16)^2 = (12)^2 = 144" />
- <InlineMath math="(29-16)^2 = (13)^2 = 169" />
- <InlineMath math="(32-16)^2 = (16)^2 = 256" />
- <InlineMath math="(36-16)^2 = (20)^2 = 400" />

Sum all these squared results (<InlineMath math="\sum(x_i - \bar{x})^2" />):

<BlockMath math="225 + 169 + 144 + 121 + 81 + 64 + 16 + 121 + 144 + 169 + 256 + 400 = 1910" />

Calculate the Variance:

<BlockMath math="\sigma^2_{\text{Group 2}} = \frac{\sum(x_i - \bar{x})^2}{n} = \frac{1910}{12} \approx 159.17" />

Calculate the Standard Deviation:

<BlockMath math="\sigma_{\text{Group 2}} = \sqrt{159.17} \approx 12.62" />

### Interpreting the Results

- Variance of Group 1 (<InlineMath math="\sigma^2 = 2" />) is **much smaller** than the Variance of Group 2 (<InlineMath math="\sigma^2 \approx 159.17" />).
- Standard Deviation of Group 1 (<InlineMath math="\sigma \approx 1.41" />) is also **much smaller** than the Standard Deviation of Group 2 (<InlineMath math="\sigma \approx 12.62" />).

These results show that the age data in **Group 1 is very clustered and uniform** around the mean of 16, whereas the age data in **Group 2 is widely spread out** far from the mean of 16.

## Alternative Formula for Variance

There's another way to calculate variance that is sometimes easier with a calculator or computer, especially for large datasets. The formula is:

<BlockMath math="\sigma^2 = \frac{\sum x_i^2}{n} - \left( \frac{\sum x_i}{n} \right)^2" />

This formula says: "Calculate the square of each data point and sum them up (<InlineMath math="\sum x_i^2" />), divide by n. Then subtract the square of the mean (<InlineMath math="(\bar{x})^2 = (\frac{\sum x_i}{n})^2" />)".

Let's recalculate the variance for Group 1 using this formula:

1.  Calculate <InlineMath math="\sum x_i^2" /> for Group 1:

    <div className="flex flex-col gap-4">
      <BlockMath math="13^2 + 14^2 + 15^2 + 15^2 + 16^2 + 16^2 + 17^2 + 17^2 + 17^2 + 17^2 + 17^2 + 18^2" />
      <BlockMath math="= 169 + 196 + 225 + 225 + 256 + 256 + 289 + 289 + 289 + 289 + 289 + 324 = 3096" />
    </div>

2.  Calculate <InlineMath math="\sum x_i" /> for Group 1:

    <div className="flex flex-col gap-4">
      <BlockMath math="13 + 14 + 15 + 15 + 16 + 16 + 17 + 17 + 17 + 17 + 17 + 18" />
      <BlockMath math="= 192" />
    </div>

    We also know <InlineMath math="n=12" />.

3.  Plug into the alternative formula:

    <div className="flex flex-col gap-4">
      <BlockMath math="\sigma^2 = \frac{3096}{12} - \left( \frac{192}{12} \right)^2" />
      <BlockMath math="\sigma^2 = 258 - (16)^2" />
      <BlockMath math="\sigma^2 = 258 - 256 = 2" />
    </div>

The result is **exactly the same** as the first method! (<InlineMath math="\sigma^2 = 2" />).