Skip to content
Statculator

Normal Distribution Calculators

Free normal distribution calculators: probabilities below, above or between values, inverse normal, z-scores, percentiles and the 68-95-99.7 rule.

Open the Normal Distribution Calculator

Updated · Formulas and conventions follow our methodology

In short

The normal distribution is the symmetric, bell-shaped curve defined by its mean μ and standard deviation σ. Test scores, heights and measurement errors are often close to normal, and sample means become approximately normal as the sample size grows. The calculators on this hub find the area below, above, between or outside values on any normal curve, turn an area back into a value, and convert between raw scores, z-scores and percentiles.

Enter a mean, a standard deviation and one or two values in the Normal Distribution Calculator to get the probability with the curve shaded and every step shown.

  • P(X < x) and P(X > x)
  • P(a < X < b) between two values
  • P(X < a or X > b) outside two values
  • z-score for each value
  • Shaded bell curve
  • Step-by-step working
Open the Normal Distribution Calculator

All 8 normal distribution calculators

Standardize, then read the area

Every normal distribution has the same shape; only the center and the width change. Subtracting the mean and dividing by the standard deviation, z = (x − μ) / σ, turns any normal variable into the standard normal Z, with mean 0 and standard deviation 1. The probability you want is then an area under that one curve: Φ(z) to the left of z, 1 − Φ(z) to the right. That is why a single normal distribution table, the z table, serves every normal problem. The calculators here do the same lookup exactly, without rounding z to two decimal places, for any mean and standard deviation.

Normal problems run in two directions. Forward, from a value to a probability: what share of scores fall below 130? Use the Normal Distribution Calculator, the Z-Score Probability Calculator or the Z-Score to Percentile Calculator. Inverse, from a probability to a value: what score marks the top 10%? Use the Inverse Normal Distribution Calculator, the Percentile to Z-Score Calculator or the Raw Score Calculator. For quick 1σ, 2σ and 3σ ranges, the Empirical Rule Calculator applies the 68-95-99.7 rule; the exact shares are 68.27%, 95.45% and 99.73%.

How to find a normal probability

  1. Write the question as an area. “Less than x” is P(X < x), “more than x” is P(X > x), “between a and b” is P(a < X < b), and “outside a and b” is P(X < a) + P(X > b). For a continuous distribution, < and ≤ give the same answer.
  2. Standardize each value with z = (x − μ) / σ.
  3. Read the left-tail area Φ(z) from the z table or a calculator.
  4. Combine the areas. Use 1 − Φ(z) for a right tail, Φ(z_b) − Φ(z_a) for an interval, and 1 minus the interval for the two outer tails.
  5. Check the answer against the curve. A value above the mean must have a left-tail area above 0.5; a value two standard deviations out leaves about 2.3% in its tail.

Normal distribution worked examples

One example for each kind of question. Each one runs in the Normal Distribution Calculator or the Inverse Normal Distribution Calculator with the same inputs.

Below a value: IQ under 120

Problem. IQ scores are scaled to a normal distribution with μ = 100 and σ = 15. What share of people score below 120?

  1. 01Standardize 120.
    z = (120 − 100) / 15 = 1.333
  2. 02Take the left-tail area.
    P(X < 120) = Φ(1.333) = 0.9088

Answer. About 90.9% of people score below 120, so 120 sits near the 91st percentile.

Above a value: heights over 75 inches

Problem. Suppose adult heights in a group are normal with μ = 69 in and σ = 3 in. What share are taller than 75 in?

  1. 01Standardize 75.
    z = (75 − 69) / 3 = 2
  2. 02Take the right tail, the complement of the left-tail area.
    P(X > 75) = 1 − Φ(2) = 1 − 0.9772 = 0.0228

Answer. About 2.3% are taller than 75 inches, roughly 1 person in 44.

Between two values: exam scores from 60 to 84

Problem. Exam scores are normal with μ = 72 and σ = 8. What share of students score between 60 and 84?

  1. 01Standardize both values.
    z₁ = (60 − 72) / 8 = −1.5
    z₂ = (84 − 72) / 8 = 1.5
  2. 02Subtract the smaller left-tail area from the larger.
    P(60 < X < 84) = Φ(1.5) − Φ(−1.5) = 0.9332 − 0.0668 = 0.8664

Answer. About 86.6% of students score between 60 and 84.

Outside two values: bolts out of tolerance

Problem. Bolt lengths are normal with μ = 10 mm and σ = 0.02 mm. Bolts shorter than 9.95 mm or longer than 10.05 mm are rejected. What share is rejected?

  1. 01Standardize both limits.
    z = (9.95 − 10) / 0.02 = −2.5
    z = (10.05 − 10) / 0.02 = 2.5
  2. 02Add the two tail areas; by symmetry they are equal.
    P(outside) = Φ(−2.5) + 1 − Φ(2.5) = 2 × 0.0062 = 0.0124

Answer. About 1.24% of bolts are rejected, roughly 1 in 81.

Inverse: the score that marks the top 10%

Problem. With exam scores normal, μ = 72 and σ = 8, what score do students need to finish in the top 10%?

  1. 01The top 10% starts at the 90th percentile, so find the z with a left-tail area of 0.90.
    z = Φ⁻¹(0.90) = 1.2816
  2. 02Convert z back to a raw score.
    x = μ + zσ = 72 + 1.2816 × 8 = 82.25

Answer. A score of about 82.3 or higher puts a student in the top 10%.

Which normal distribution calculator should I use?

If you want to…Use
If you want P(X < x), P(X > x) or P(a < X < b) for any mean and standard deviation
If you know an area or percentile and want the matching x value
If you want to standardize a value into a z-score
If you already have z and want the area under the standard normal curve
If you want to turn a z-score into a percentile rank
If you want the z-score at a given percentile, such as the 90th
If you have a z-score and want the original value back
If you want quick ranges for 1, 2 and 3 standard deviations
If you are approximating a binomial probability with a normal curve

Normal distribution formulas

ConceptFormulaExample (μ = 100, σ = 15)
z-scorez = (x − μ) / σx = 130 gives z = 2
Raw scorex = μ + zσz = −1 gives x = 85
Density (PDF)f(x) = e^(−(x − μ)² / (2σ²)) / (σ√(2π))Highest at x = 100
Left-tail probability (CDF)P(X ≤ x) = Φ(z)P(X ≤ 130) = 0.9772
Right-tail probabilityP(X ≥ x) = 1 − Φ(z)P(X ≥ 130) = 0.0228
Between two valuesP(a ≤ X ≤ b) = Φ(z_b) − Φ(z_a)P(85 ≤ X ≤ 115) = 0.6827
Inverse normalx = μ + σ · Φ⁻¹(p)90th percentile = 119.22
Empirical ruleμ ± 1σ, 2σ, 3σ contain about 68%, 95%, 99.7%85–115, 70–130, 55–145

Normal distribution terms

TermMeaning
Normal distributionA continuous, symmetric, bell-shaped distribution set by its mean μ and standard deviation σ. Also called the Gaussian distribution or bell curve.
Standard normal distributionThe normal distribution with μ = 0 and σ = 1, written Z. Every normal variable becomes Z after standardizing.
Random variableA quantity whose value depends on chance, such as the score of a randomly chosen student. X usually denotes a normal variable.
Mean, μThe center of the curve. The mean, median and mode of a normal distribution are equal.
Standard deviation, σThe typical distance from the mean. It sets how wide the curve is; the inflection points sit at μ ± σ.
Raw scoreAn original value x, in the units of the data, such as an IQ of 120 or a height of 75 inches.
z-scoreThe number of standard deviations a raw score lies from the mean: z = (x − μ) / σ.
ProbabilityFor a continuous distribution, the area under the curve over a range of values. The area under the whole curve is 1.
Cumulative probability, Φ(z)The area to the left of a value, P(X ≤ x). The cumulative distribution function (CDF) gives it, and the z-table lists it.
PercentileThe cumulative probability written as a percentage: a value with Φ(z) = 0.84 is at the 84th percentile.

Frequently asked questions

What is the standard normal distribution?

The standard normal distribution is the normal distribution with mean 0 and standard deviation 1, usually written Z. Any normal variable X becomes standard normal after the transformation z = (x − μ) / σ. Its cumulative probabilities are listed in the z table.

How do I find a probability from a z-score?

The probability below a z-score is the area to its left under the standard normal curve, Φ(z). The area above is 1 − Φ(z), and the area between two z-scores is the difference of their Φ values. For z = 1.5, P(Z < 1.5) = 0.9332 and P(Z > 1.5) = 0.0668. The Z-Score Probability Calculator returns all of these areas at once.

What percentage of the data is below a z-score of −1?

For a normal distribution, 15.87% of values lie below z = −1, so it marks roughly the 16th percentile. The other 84.13% lie above it, and 68.27% lie between z = −1 and z = 1. With μ = 100 and σ = 15, z = −1 corresponds to a raw score of 85.

What percentage of data falls within 1, 2 and 3 standard deviations of the mean?

For a normal distribution, 68.27% of values lie within 1 standard deviation of the mean, 95.45% within 2, and 99.73% within 3. These are usually rounded to 68%, 95% and 99.7%, the empirical rule. The rule does not apply to strongly skewed data.

What is the difference between a z-score and a percentile?

A z-score says how many standard deviations a value lies from the mean, while a percentile says what percentage of the distribution lies below it. For normal data they map one-to-one: z = 0 is the 50th percentile, z = 1 is about the 84th, and z = 1.645 is the 95th. Convert in either direction with the Z-Score to Percentile Calculator and the Percentile to Z-Score Calculator.

How do I calculate normal probabilities on a TI-84 or in Excel?

On a TI-84, normalcdf(lower, upper, μ, σ) gives the area between two values; use −1E99 or 1E99 for an open tail. invNorm(area, μ, σ) returns the value with that left-tail area. In Excel, NORM.DIST(x, μ, σ, TRUE) gives P(X ≤ x), NORM.INV(p, μ, σ) gives the inverse, and NORM.S.DIST(z, TRUE) and NORM.S.INV(p) do the same for the standard normal.

How can I tell if my data are approximately normal?

Plot a histogram or box plot and look for a single peak, rough symmetry and no extreme outliers. Skewness and excess kurtosis close to zero support normality, and you can compute both with the Skewness Calculator and Kurtosis Calculator. Small samples rarely look perfectly normal, so judge the overall shape rather than every bump. For a formal test, use the Shapiro–Wilk Test Calculator.

Looking for something else? See all calculators or search the site.