The phrase “what does what the sigma mean” typically refers to the Greek letter sigma in a statistics formula. In most statistics contexts, the symbol \( \sigma \) means population standard deviation, a numerical measure of how spread out the population values are around the population mean \( \mu \).
1) The core meaning: \( \sigma \) as population standard deviation
Consider a population with values \(x_1, x_2, \ldots, x_N\) and population mean \( \mu \). The population variance is \( \sigma^2 \), and the population standard deviation is \( \sigma \):
\[ \sigma^2 = \frac{1}{N}\sum_{i=1}^{N}(x_i - \mu)^2, \qquad \sigma = \sqrt{\sigma^2}. \]
Interpretation: larger \( \sigma \) indicates greater dispersion; smaller \( \sigma \) indicates values cluster more tightly around \( \mu \).
2) Distinguishing \( \sigma \) from s (sample standard deviation)
In practice, data often come from a sample of size \(n\), not an entire population. The sample mean is \(\bar{x}\), and the sample variance and standard deviation are usually denoted \(s^2\) and \(s\):
\[ s^2 = \frac{1}{n-1}\sum_{i=1}^{n}(x_i - \bar{x})^2, \qquad s = \sqrt{s^2}. \]
Why \(n-1\) appears: using \(n-1\) (Bessel’s correction) makes \(s^2\) an unbiased estimator of the population variance \( \sigma^2 \) under standard sampling assumptions.
3) Distinguishing \( \sigma \) from capital sigma \( \Sigma \) (summation)
The capital sigma \( \Sigma \) is not a standard deviation symbol; it is an instruction to add terms. For example:
\[ \sum_{i=1}^{N}(x_i - \mu)^2 \]
means “add the squared deviations \((x_i-\mu)^2\) from \(i=1\) to \(N\).” The standard deviation \( \sigma \) is obtained only after averaging (divide by \(N\) for a population) and taking the square root.
4) Quick reference table
| Symbol | Typical meaning in statistics | Common formula (where applicable) |
|---|---|---|
| \(\sigma\) | Population standard deviation (spread of a population) | \(\sigma=\sqrt{\frac{1}{N}\sum_{i=1}^{N}(x_i-\mu)^2}\) |
| \(\sigma^2\) | Population variance | \(\sigma^2=\frac{1}{N}\sum_{i=1}^{N}(x_i-\mu)^2\) |
| \(s\) | Sample standard deviation (estimate of population spread) | \(s=\sqrt{\frac{1}{n-1}\sum_{i=1}^{n}(x_i-\bar{x})^2}\) |
| \(\Sigma\) or \(\sum\) | Summation operator (“add these terms”) | \(\sum_{i=1}^{n} a_i = a_1 + a_2 + \cdots + a_n\) |
5) Worked numeric example
Suppose a population consists of the five values \( \{2,4,4,4,6\} \). The population mean is:
\[ \mu=\frac{2+4+4+4+6}{5}=\frac{20}{5}=4. \]
Compute squared deviations and sum them:
\[ \sum (x_i-\mu)^2 = (2-4)^2+(4-4)^2+(4-4)^2+(4-4)^2+(6-4)^2 =4+0+0+0+4=8. \]
Then:
\[ \sigma^2=\frac{8}{5}=1.6, \qquad \sigma=\sqrt{1.6}\approx 1.2649. \]
6) Visualization: how \( \sigma \) controls spread in a normal model
7) Practical reading tip in inference problems
- If a problem states “\( \sigma \) is known,” it indicates the population standard deviation is treated as given and methods based on the standard normal distribution are typically used.
- If \( \sigma \) is unknown and replaced by \(s\), inference often uses the t distribution (under standard assumptions).