Écart type Calculatrice

Saisie de Données

Séparez les valeurs par des virgules, des espaces, des tabulations ou des sauts de ligne
0 valeurs saisies

Entrez des valeurs de données pour voir les résultats

What Is Standard Deviation?

Standard deviation measures how far values typically sit from the mean of a data set. It is written σ when the data is a whole population and s when it is a sample. Unlike variance, it is in the same units as your data, so a standard deviation of 3 kg means something you can picture directly. A small value means the numbers are bunched close to the mean; a large value means they are spread out. This calculator gives you both the population and the sample standard deviation, and the variance they come from.

Formula

There are two versions. They differ only in what you divide by before taking the square root.

Population Standard Deviation

σ = √[ Σ(xᵢ − μ)² / N ]
  • σPopulation standard deviation
  • xᵢEach individual data value
  • μPopulation mean
  • NNumber of values in the population

Sample Standard Deviation

s = √[ Σ(xᵢ − x̄)² / (n − 1) ]
  • sSample standard deviation
  • x̄Sample mean
  • n − 1Degrees of freedom (Bessel's correction)

How to Calculate Standard Deviation Step by Step

  1. Calculate the mean.Add all values and divide by the count.
  2. Find each deviation.Subtract the mean from every value: (xᵢ − x̄).
  3. Square the deviations.Squaring removes the minus signs: (xᵢ − x̄)².
  4. Add the squares.This total is the sum of squares, Σ(xᵢ − x̄)².
  5. Divide.Divide by N for a population or by n − 1 for a sample. The result is the variance.
  6. Take the square root.The square root of the variance is the standard deviation.

Standard Deviation Examples

1Student Test Scores (sample)

Data:72, 85, 90, 68, 95
Solution:Mean = (72 + 85 + 90 + 68 + 95) / 5 = 82. Squared deviations: 100, 9, 64, 196, 169. Sum of squares = 538. Sample variance = 538 / 4 = 134.5.
Answer:Sample standard deviation (s) ≈ 11.60

2Daily Temperatures for One Week's Weekdays (°C, population)

Data:20, 22, 19, 23, 21
Solution:Mean = 21. Squared deviations: 1, 1, 4, 4, 0. Sum of squares = 10. Population variance = 10 / 5 = 2.
Answer:Population standard deviation (σ) ≈ 1.41

3Product Weights (grams, sample)

Data:500, 502, 498, 501, 499
Solution:Mean = 500. Squared deviations: 0, 4, 4, 1, 1. Sum of squares = 10. Sample variance = 10 / 4 = 2.5.
Answer:Sample standard deviation (s) ≈ 1.58

4Monthly Rainfall (mm), both versions

Data:50, 75, 30, 90, 60
Solution:Mean = 61. Deviations: −11, 14, −31, 29, −1. Squared: 121, 196, 961, 841, 1. Sum of squares = 2120. Population variance = 2120 / 5 = 424. Sample variance = 2120 / 4 = 530.
Answer:σ ≈ 20.59 | s ≈ 23.02

5Household Energy Bills ($), both versions

Data:95, 110, 87, 102, 98, 115
Solution:Mean ≈ 101.17. Sum of squares ≈ 518.83. Population variance ≈ 86.47. Sample variance ≈ 103.77.
Answer:σ ≈ 9.30 | s ≈ 10.19

How to Use This Standard Deviation Calculator

Paste or type your numbers and the results update straight away:

  1. Enter your values separated by commas, spaces or line breaks. You can paste a column from a spreadsheet.
  2. Choose Sample if your numbers are drawn from a larger group, or Population if they are the whole group.
  3. Read the standard deviation, variance, mean and the other summary figures.
  4. Open "Show Calculation Steps" to see every deviation and squared deviation, then copy the results if you need them.

What the Calculator Shows You

  • Both the sample and the population result, so you can see the effect of the n − 1 correction.
  • The full working: mean, each deviation, each squared deviation and the sum of squares.
  • The mean, range, sum of squares and coefficient of variation from the same input.
  • A chart of your values with the mean and a ±1 standard deviation band.
  • Calculations run in your browser; your numbers are not sent anywhere.

Where Standard Deviation Is Used

Education

Seeing whether a class's marks are tightly grouped or widely spread.

Finance

Volatility of returns is usually reported as a standard deviation.

Manufacturing

Control charts set their limits a fixed number of standard deviations from the target.

Healthcare research

Results tables report "mean ± SD" for measurements such as blood pressure.

Sport

Comparing how consistent two athletes' times or scores are.

Weather

Describing how much daily temperatures vary around the monthly average.

Common Mistakes When Calculating Standard Deviation

These are the errors that most often lead to a wrong answer:

Using the wrong divisor

Dividing by N when your data is a sample makes the result too small. Use n − 1 unless you really do have every member of the group.

Forgetting to square the deviations

Raw deviations from the mean always add up to zero, so averaging them tells you nothing.

Forgetting the square root

If your answer is in squared units, you have calculated the variance, not the standard deviation.

Mixing units

Values recorded partly in centimetres and partly in metres give a meaningless result. Convert everything first.

Rounding too early

Rounding the mean before computing deviations introduces errors that grow through the calculation. Keep full precision until the end.

Standard Deviation or Variance: Which Should You Report?

They describe the same spread. The right one depends on who will read it and what happens next.

For people reading the result, use standard deviation

It is in the same units as the data. "The average is 50 ± 5 kg" is easy to picture; "the variance is 25 kg²" is not.

For further calculation, use variance

Variances of independent quantities add: Var(X + Y) = Var(X) + Var(Y). Standard deviations do not, which is why ANOVA and regression work with variances.

For the 68–95–99.7 rule, use standard deviation

For roughly normal data, about 68% of values fall within one standard deviation of the mean, 95% within two and 99.7% within three.

Converting is one step

Variance = SD². SD = √variance. You never need to recalculate from the raw data to switch between them.

Foire Aux Questions: Écart type Calculatrice

Tout ce que vous devez savoir sur la variance.

Quel est l’écart type de 1, 2, 3, 4, 5 ?

L'écart type de 1, 2, 3, 4, 5 est calculé comme suit. Moyenne = 3. Écarts au carré : 4, 1, 0, 1, 4. Somme des carrés = 10. Écart type de la population (σ) = √(10/5) = √2 ≈ 1,414. Écart type (s) de l'échantillon = √(10/4) = √2,5 ≈ 1,581. Utilisez SD de population s'il s'agit de tous vos points de données ; utilisez l’échantillon SD s’ils représentent un échantillon d’un groupe plus large.

Comment calculer l’écart type étape par étape ?

Pour calculer l'écart type étape par étape : 1. Recherchez la moyenne (moyenne) de votre ensemble de données. 2. Soustrayez la moyenne de chaque valeur pour obtenir les écarts. 3. Mettez au carré chaque écart. 4. Trouvez la moyenne des écarts carrés (divisez par n pour la population, n−1 pour l'échantillon). Cela vous donne la variance. 5. Prenez la racine carrée de la variance. Le résultat est l’écart type. Notre calculatrice affiche automatiquement chaque étape.

Quelle est la différence entre l’écart type et la variance ?

L'écart type est la racine carrée de la variance. La variance mesure la répartition en unités carrées, tandis que l'écart type la reconvertit dans les unités d'origine de vos données. Par exemple, si vos données sont en mètres, la variance est en mètres², mais l'écart type est en mètres. L'écart type est généralement plus facile à interpréter car il utilise la même échelle que les données brutes.

Comment calculer l’écart type dans Excel ?

Dans Excel, utilisez STDEV.S(range) pour l'écart type de l'échantillon et STDEV.P(range) pour l'écart type de la population. Exemple : =STDEV.S(A1:A10). Dans Google Sheets, les mêmes fonctions fonctionnent. En Python, utilisez np.std(data, ddof=1) pour l'exemple SD. Dans R, sd(x) renvoie l'écart type de l'échantillon par défaut.

Qu'est-ce qu'un bon écart type ?

Il n’existe pas d’écart type universellement « bon » – cela dépend du contexte. Un faible écart type signifie que les points de données se regroupent étroitement autour de la moyenne (plus cohérents). Un écart type élevé signifie que les données sont largement réparties (plus variables). Lors du contrôle qualité, une faible SD est préférable pour des raisons de cohérence. En investissement, un SD plus élevé indique plus de risque. Utilisez le coefficient de variation (CV) pour comparer la répartition entre des ensembles de données à différentes échelles.

L’écart type peut-il être négatif ?

Non, l'écart type ne peut jamais être négatif. Il s'agit de la racine carrée de la variance, et la variance est toujours nulle ou positive (car elle additionne les carrés des différences). Un écart type de 0 signifie que toutes les valeurs sont identiques. Tout écart dans les données produit un écart type positif.

Should I report the standard deviation or the variance?

Report the standard deviation when people need to read the result, because it is in the same units as the data ("heights vary by about 2.5 inches"). Use the variance when you are doing further maths with it: in ANOVA and regression, and when combining independent variables, variances add but standard deviations do not.

Can the standard deviation be larger than the variance?

Yes, whenever the variance is between 0 and 1. For a variance of 0.25 the standard deviation is √0.25 = 0.5, which is larger. They are equal at 1 (and at 0), and for any variance above 1 the standard deviation is smaller, e.g. variance 4 gives SD 2.