Skip to main content

FREE ADVANCED STATISTICS CALCULATOR

Standard deviation calculator with variance, quartiles, and descriptive statistics.

Standard deviation is the typical distance of your values from their mean. Paste raw data, a frequency table or grouped classes to get the sample or population SD with steps, plus the variance, mean, median, quartiles and IQR.

DATA WORKSPACE

Input and options

sample
Select the results you want

RESULT

Ready

No data
σ

Choose a data type, select the statistics you need, then calculate.

STATISTICS FORMULAS EXPLAINED

Understand the result before you use it.

Standard deviation tells you how far values typically sit from the mean: small means the answers are similar, large means they are spread out. Choose the data format first, then decide whether your values are a sample (most theses) or the whole population.

STANDARD DEVIATION

Sample vs population SD

Use sample standard deviation when your values are only part of a larger group. Use population standard deviation when the values are the complete population being studied.

VARIANCE

Average squared spread

Variance measures average squared distance from the mean. Standard deviation is the square root of variance, so it is easier to read in the original unit.

QUARTILES AND IQR

Middle spread of the data

Q1, Q3, and IQR help explain spread without being controlled by very large or very small values. IQR is useful when checking possible outliers.

FREQUENCY TABLES

Repeated values and grouped intervals

Use discrete frequency rows when exact values repeat. Use grouped data when values are already summarized into class intervals such as 10–20 or 20–30.

LINEAR REGRESSION

Paired X/Y relationship

Paired mode calculates slope, intercept, correlation, R², covariance, and an optional predicted y-value for a selected x-value.

OUTLIERS

1.5 × IQR rule

The outlier count uses the common IQR fence method: values below Q1 − 1.5×IQR or above Q3 + 1.5×IQR are flagged as possible outliers.

WORKED EXAMPLE

How sample standard deviation is calculated.

For the raw data set 58, 64, 72, 72, 78, 84, 91, the mean is about 74.14. With sample mode selected, the calculator divides the squared deviations by n − 1.
Sample variances² = Σ(x − x̄)² ÷ (n − 1)

For the example data, sample variance is about 128.14.

Sample standard deviations = √128.14 ≈ 11.32

The typical distance from the mean is about 11.32 data units.

Population standard deviationσ = √(Σ(x − μ)² ÷ n)

Use this only when your entered values are the full population.

COMMON QUESTIONS

Quick answers for statistics problems.

What is the formula for sample standard deviation?

Subtract the mean from each value, square each difference, add them, divide by n − 1, then take the square root.

What is the difference between variance and standard deviation?

Variance is squared spread. Standard deviation is the square root of variance, so it is easier to compare with the original data unit.

When should I use grouped data?

Use grouped data when you only have class intervals and frequencies. The calculator estimates mean and spread using each class midpoint.

Can this calculator do linear regression?

Yes. Choose paired X/Y mode to calculate slope, intercept, correlation r, R², covariance, and optional prediction.

Read the standard deviation formula guide →Use Graphing Calculator for visual checks →

METHOD

Standard deviation calculator: worked examples and what to report

What does this standard deviation calculator give you?

Choose Sample (n − 1) or Population (n) and it returns that standard deviation, together with the mean, variance, median, quartiles, IQR, coefficient of variation and an outlier check. Use the sample SD for survey and thesis data unless you measured every member of the group.

Worked example: raw scores

  1. Enter 58, 64, 72, 72, 78, 84, 91 in raw data mode.
  2. Mean = 519 ÷ 7 = 74.14.
  3. Sum of squared deviations = 768.86.
  4. Sample SD s = √(768.86 ÷ 6) = 11.32; population SD σ = √(768.86 ÷ 7) = 10.48.
  5. Report it as M = 74.14, SD = 11.32.

Worked example: Likert responses entered as a frequency table

  1. Choose frequency table mode and enter values 1–5 with counts 2, 3, 8, 5, 2 (N = 20).
  2. Mean = Σfx ÷ N = 62 ÷ 20 = 3.10.
  3. Σf(x − x̄)² = 23.80, so s = √(23.80 ÷ 19) = 1.12.
  4. Report it as M = 3.10, SD = 1.12 (N = 20).

Worked example: grouped data with class intervals

  1. Choose grouped data mode and enter 10–19, 20–29, 30–39, 40–49 with frequencies 4, 7, 6, 3.
  2. The calculator uses the class midpoints 14.5, 24.5, 34.5 and 44.5.
  3. Mean = 570 ÷ 20 = 28.5 and Σf(m − x̄)² = 1,880.
  4. Estimated sample SD = √(1,880 ÷ 19) = 9.95.

Is my standard deviation high or low?

Judge it against the scale. On a 5-point Likert item, an SD under about 1.0 means respondents mostly agreed with each other, while an SD above about 1.5 means opinions were split. For other data, the coefficient of variation (SD ÷ mean) lets you compare spread between variables with different units.