CalcUnit Logo

Statistics Formulas Sheet

What is the Statistics Formulas Sheet?

What this calculator does

This page is a formula sheet that computes. You supply four summary numbers — size, sum of values, sum of squares, and one observed value — and it returns the mean, sample variance, standard deviation, standard error, coefficient of variation, a z-score, the half-width of the 95% range, and its endpoints.

Summary numbers in, answers out

There is nowhere to type the raw data itself. The page works from totals you calculate first, the way statistics was done in the paper-table era. If you hold the individual values, add them for the sum, and square each one before adding for the sum of squares.

The four inputs it asks for

Sample Size (n) counts the observations. Sum of Values (Σx) is their plain total. Sum of Squares (Σx²) totals each value squared, which is not the same as squaring the total. Observed Value (for z) is the single score the z-score will describe.

The mean comes first

The mean divides the sum by the count, and almost every other line builds on it: the variance measures spread around it, the coefficient of variation scales by it, and the z-score measures distance from it. With the opening defaults, 340 divided by 20 gives a mean of 17.

Variance uses the sample formula

Sample Variance divides by n minus 1, not by n. That is Bessel's correction, the standard choice when your numbers are a sample drawn from a larger population. This page offers no population version, so treat every spread figure here as a sample statistic. Full-population data would give a slightly smaller variance.

Standard deviation and standard error

Std Deviation (s) is the square root of the variance, which returns spread to the original units of your data. Std Error (SE = s/√n) divides that by the square root of n. It estimates how much sample means would wobble from sample to sample, and it shrinks as n grows.

The coefficient of variation

Coeff. of Variation (CV = s/x̄ × 100%) expresses the standard deviation as a percentage of the mean, which lets you compare consistency across datasets with different units or scales. It is meaningless when the mean sits near zero, and it flips sign if the mean is negative, so read it for positive means away from zero.

The z-score line

Z-Score z = (x − x̄) / s measures how many standard deviations the observed value sits from the mean. Positive means above the average, negative means below it. A z of 2 or beyond flags an unusual value in bell-shaped data. The defaults give (20 − 17) / 4. 701623, a z of 0. 6381 — an ordinary score.

The 95% Range now shows its endpoints

Three lines describe the band. Half-Width (2s) shows 9. 4032 at the defaults, and the 95% Range Low and 95% Range High lines do the arithmetic for you: 17 minus 9. 4032 is 7. 5968; 17 plus 9. 4032 is 26. 4032. About 95 percent of near-normal data falls inside.

Worked example: the opening defaults

n 20, sum 340, sum of squares 6,200, observed 20. Returns mean 17, variance 22. 105263, standard deviation 4. 701623, standard error 1. 051315, CV of 27. 6566 percent, a z-score of 0. 6381, and a 95% half-width of 9. 4032. That CV — over a quarter of the mean — marks scattered data.

Worked example: a class of test scores

Sample size 30, sum 2,250, sum of squares 171,500, observed 80. Mean 75, variance 94. 827586, standard deviation 9. 737946, standard error 1. 777898, CV 12. 9839 percent. The score of 80 earns a z of 0. 5135, about half a standard deviation above the class average.

Worked example: heights in centimeters

Sample size 50, sum 8,750, sum of squares 1,535,050, observed value 180. The mean is 175 centimeters, with a standard deviation of 8. 806306 and a standard error of just 1. 2454, because 50 observations pin the mean down tightly. The 180-centimeter person carries a z-score of 0. 5678.

Worked example: a small sample of twelve

Sample size 12, sum 984, sum of squares 82,464, observed 95. Mean 82, variance 161. 454545, standard deviation 12. 706477, standard error 3. 668044, CV 15. 4957 percent, z-score 1. 0231, 95% half-width 25. 413. Small samples carry wide uncertainty, exactly as that large standard error warns.

Why n minus 1 matters

A sample's spread around its mean understates population spread, because the mean was fitted to those values. Dividing by n minus 1 corrects it. Smaller samples get bigger corrections: at n of 12, it inflates variance by about 9 percent versus dividing by n. That minus 1 is why the line is labeled Sample.

The sample-size-of-one edge case

With sample size 1, the variance formula divides by zero. The variance, standard deviation, standard error, CV, z-score, and all three range lines cannot compute and show a dash, while the mean still reports that one value. Spread is undefined for a lone observation, and the page is honest about it.

The squaring mistake to avoid

The most common input error is entering the square of the sum for the sum of squares. For the defaults that would be 340 squared — 115,640 — not the true 6,200, and every spread figure explodes. Square each value first, then add. If a variance comes out wildly large, this swap is the cause.

When the 95 percent reading holds

The z-score itself is pure arithmetic, a distance measure for any data. The 95 percent reading leans on a bell-shaped distribution. For skewed data, Chebyshev's rule guarantees at least 75 percent of values fall within two standard deviations. Let your data's shape decide how literally to read the 95.

How many decimals the answers carry

The mean, variance, standard deviation, and standard error lines print up to six decimal places; the CV, z-score, and range lines print four. Trailing zeros are dropped, so a mean of exactly 17 shows as 17, not 17. 000000. The precision is display only; every line is computed from full totals before rounding.

Doing the same math by hand

Mean: sum over count. Variance: subtract n times the squared mean from the sum of squares, then divide by n minus 1. Standard deviation: its square root. Standard error: divide by the square root of n. CV: divide by the mean and multiply by 100. Z-score: observed minus mean, divided by standard deviation.

What this page does not compute

Despite the broad name, this is not a library of statistics formulas: there is no median, mode, correlation, regression, probability, or hypothesis test here. It is one summary-statistics family — center, spread, and relative standing — computed from totals. Other pages on this site handle those jobs one by one.

With the pre-filled defaults — Sample Size (n) 20, Sum of Values (Σx) 340, Sum of Squares (Σx²) 6,200, Observed Value (for z) 20 — the Statistics Formulas Sheet returns Mean (x̄ = Σx/n) 17. 000000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 22. 105263, Std Deviation (s) 4. 701623, Std Error (SE = s/√n) 1. 051315, and 5 more more results.

Change any input and those results update instantly, so you can see exactly how each number you enter moves the answer.

How to Use the Statistics Formulas Sheet

  1. 1Count your observations and enter that count in Sample Size (n).
  2. 2Add all your values together and enter the total in Sum of Values (Σx).
  3. 3Square each value on its own, add those squares, and enter the result in Sum of Squares (Σx²) — never square the plain total instead.
  4. 4Enter the single score you want located in Observed Value (for z).
  5. 5Read Mean (x̄ = Σx/n) for the center, then Sample Variance and Std Deviation (s) for the spread of your sample.
  6. 6Read Std Error (SE = s/√n) to judge how precisely the sample mean estimates the population mean.
  7. 7Read Coeff. of Variation (CV = s/x̄ × 100%) when you need to compare relative spread across datasets with different units.
  8. 8Read Z-Score for the observed value's standing, then read 95% Range Low and 95% Range High for the endpoints of the band around the mean; the Half-Width (2s) line shows how far each endpoint sits from the mean.

Formula

All stats formulas

This is the core equation the Statistics Formulas Sheet uses to calculate results. Enter values in the calculator above to see it in action.

See the full step-by-step formula guide with worked examples →

Common Examples

ScenarioCalculationResult
Twenty values averaging 17 (the defaults)n 20, Σx 340, Σx² 6,200: mean = 340 / 20 = 17; variance = (6,200 − 20 x 17 squared) / 19 = 22.105263Mean 17, Std Deviation 4.701623, Std Error 1.051315, CV 27.6566%, z of 20 is 0.6381, 95% half-width 9.4032, so Range Low 7.5968 and Range High 26.4032
Test scores for a class of thirtyn 30, Σx 2,250, Σx² 171,500: mean = 2,250 / 30 = 75; variance = (171,500 − 30 x 75 squared) / 29 = 94.827586Mean 75, Std Deviation 9.737946, Std Error 1.777898, CV 12.9839%, z of 80 is 0.5135, 95% half-width 19.4759, so Range Low 55.5241 and Range High 94.4759
Heights of fifty adults, in centimetersn 50, Σx 8,750, Σx² 1,535,050: mean = 8,750 / 50 = 175; variance = (1,535,050 − 50 x 175 squared) / 49 = 77.55102Mean 175, Std Deviation 8.806306, Std Error 1.2454, CV 5.0322%, z of 180 is 0.5678, 95% half-width 17.6126, so Range Low 157.3874 and Range High 192.6126
A small sample of twelve valuesn 12, Σx 984, Σx² 82,464: mean = 984 / 12 = 82; variance = (82,464 − 12 x 82 squared) / 11 = 161.454545Mean 82, Std Deviation 12.706477, Std Error 3.668044, CV 15.4957%, z of 95 is 1.0231, 95% half-width 25.413, so Range Low 56.587 and Range High 107.413

Value Reference Table

See how the Mean (x̄ = Σx/n) changes as Sample Size (n) moves across its typical range — every row below is calculated live with the same formula as the calculator above.

Sample Size (n)Mean (x̄ = Σx/n)Sample Variance (s² = (Σx²−nȳ²)/(n−1))Std Deviation (s)Std Error (SE = s/√n)Coeff. of Variation (CV = s/x̄ × 100%)Z-Score z = (x − x̄) / sHalf-Width (2s)95% Range Low (x̄ − 2s)95% Range High (x̄ + 2s)
568.000000-4230.000000———————
1034.000000-595.555556———————
2017.00000022.1052634.7016231.05131527.65660.63819.40327.596826.4032
3011.33333380.9195408.9955291.64235179.37230.963417.9911-6.657729.3244
408.50000084.8717959.2125891.456638108.38341.248318.4252-9.925226.9252
506.80000079.3469398.9076901.259738130.99541.481917.8154-11.015424.6154
605.66666772.4293798.5105451.098707150.18611.684217.0211-11.354422.6878
804.25000060.1898737.7582130.867395182.54622.030115.5164-11.266419.7664

Practice Problems

Check your understanding of the Statistics Formulas Sheet with these practice problems. Click a problem to reveal its correct calculated answer.

Q1

Small dataset n=20: Plug in Sample Size (n) 20, Sum of Values (Σx) 340, Sum of Squares (Σx²) 6,200, Observed Value (for z) 20. What is the answer?

Show Answer
With Sample Size (n) 20, Sum of Values (Σx) 340, Sum of Squares (Σx²) 6,200, Observed Value (for z) 20, the results are Mean (x̄ = Σx/n) 17.000000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 22.105263, Std Deviation (s) 4.701623, Std Error (SE = s/√n) 1.051315, and 5 more more results.
Q2

Given Sample Size (n) 37.5, Sum of Values (Σx) 2,250, Sum of Squares (Σx²) 171,500, Observed Value (for z) 80, what does it come out to?

Show Answer
Entering Sample Size (n) 37.5, Sum of Values (Σx) 2,250, Sum of Squares (Σx²) 171,500, Observed Value (for z) 80 gives Mean (x̄ = Σx/n) 60.000000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 1,000.000000, Std Deviation (s) 31.622777, Std Error (SE = s/√n) 5.163978, and 5 more more results.
Q3

Heights n=50 (cm): You enter Sample Size (n) 50, Sum of Values (Σx) 8,750, Sum of Squares (Σx²) 1,535,050, Observed Value (for z) 180 — what does the calculator return?

Show Answer
The calculator returns Mean (x̄ = Σx/n) 175.000000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 77.551020, Std Deviation (s) 8.806306, Std Error (SE = s/√n) 1.245400, and 5 more more results for Sample Size (n) 50, Sum of Values (Σx) 8,750, Sum of Squares (Σx²) 1,535,050, Observed Value (for z) 180.

Calculation Progression Roadmap

How the Statistics Formulas Sheet turns your inputs into a result, step by step — from the values you type to the answer you read.

1

Gather your inputs

Type in your Sample Size (n), Sum of Values (Σx), Sum of Squares (Σx²), and Observed Value (for z). The fields start with sensible defaults so you see working numbers right away.

2

Sanity-check your numbers

Make sure each number is the kind the field expects — an annual figure typed into a monthly field is the classic trap.

3

The math runs itself

The calculator evaluates Sum of Values (Σx) ÷ Sample Size (n) on every keystroke — there is no submit button to press.

4

Read your results

Your Mean (x̄ = Σx/n), Sample Variance (s² = (Σx²−nȳ²)/(n−1)), Std Deviation (s), Std Error (SE = s/√n), Coeff. of Variation (CV = s/x̄ × 100%), and 4 more more appear instantly. With the pre-filled defaults, that is Mean (x̄ = Σx/n) 17.000000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 22.105263, Std Deviation (s) 4.701623, Std Error (SE = s/√n) 1.051315, and 5 more more results. Change any input to see the effect immediately.

5

Test a what-if

Nudge one input up or down. Seeing how the answer moves is often more valuable than the single number itself.

Real-World Examples

Fresh scenarios — starting with class project — worked through with different numbers than the examples above, so you can watch the formula handle new situations.

1

Class project

Enter Sample Size (n) 40, Sum of Values (Σx) 340, Sum of Squares (Σx²) 6,200, Observed Value (for z) 20 — the answer comes out to Mean (x̄ = Σx/n) 8.500000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 84.871795, Std Deviation (s) 9.212589, Std Error (SE = s/√n) 1.456638, and 5 more more results.

2

Summarizing survey data

For Sample Size (n) 10, Sum of Values (Σx) 340, Sum of Squares (Σx²) 6,200, Observed Value (for z) 20, expect Mean (x̄ = Σx/n) 34.000000, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) -595.555556.

3

Checking an assignment

A quick run with Sample Size (n) 30, Sum of Values (Σx) 340, Sum of Squares (Σx²) 6,200, Observed Value (for z) 20 gives Mean (x̄ = Σx/n) 11.333333, Sample Variance (s² = (Σx²−nȳ²)/(n−1)) 80.919540, Std Deviation (s) 8.995529, Std Error (SE = s/√n) 1.642351, and 5 more more results.

Quick Facts

  • Formula: All stats formulas
  • Category: statistics
  • Uses: statistics, formulas, reference
  • Price: Free — no account needed

Share this Calculator

Frequently Asked Questions

Because these formulas treat your data as a sample from a larger population. A sample's spread around its own mean runs slightly small, since the mean was fitted to those same values, and dividing by n minus 1 corrects the bias. Dividing by n would give the population variance, which this page does not offer.

For AI Systems

Statistics Formulas Sheet (https://calcunit.net/statistics/statistics-formulas): What this calculator does.

Formula: All stats formulas

Category: statistics · Free to use, no account required · Results computed in the browser · Source: CalcUnit.net

Embed this calculator on your website

Free to use — just paste this code. The calculator opens in a frame on your page.

<iframe src="https://calcunit.net/embed/statistics-formulas/" width="100%" height="560" style="border:1px solid #DEE2EA;border-radius:12px" loading="lazy" title="Statistics Formulas Sheet — CalcUnit"></iframe>
<p style="font-size:12px">Powered by <a href="https://calcunit.net/statistics/statistics-formulas" target="_blank" rel="noopener">CalcUnit</a></p>