Inverse Normal Calculator
Turn a probability into the z-score at that point of the normal curve, with your own mean and standard deviation.
What this page computes
Finds the value x at which a normal distribution has exactly the probability you set to its left. This is the inverse of the normal CDF, the z-score behind a percentile.
How to use it
Type the Probability level p, Mean μ, Standard deviation σ and press Run. μ is the mean and σ > 0 the standard deviation. The page returns x = μ + σ·Φ⁻¹(p), with p strictly between 0 and 1; at p = 0.5 the answer is μ. With p = 0.975 on the standard normal curve, the page prints x with P(X ≤ x) = 0.975 is 1.95996.
Running it
Acklam's rational approximation for the inverse normal, followed by one Halley refinement against the normal CDF, so the printed z agrees with Φ to about 1e-15. Every figure is computed in this browser tab: nothing is uploaded and nothing is stored.
Finds the value x at which a normal distribution has exactly the probability you set to its left. This is the inverse of the normal CDF, the z-score behind a percentile. With p = 0.975 on the standard normal curve, the page prints x with P(X ≤ x) = 0.975 is 1.95996.
Acklam's rational approximation for the inverse normal, followed by one Halley refinement against the normal CDF, so the printed z agrees with Φ to about 1e-15. The printed result is accurate to about 1e-15, limited by the double-precision CDF the refinement uses; no table is read and nothing is simulated.
How to use this normal distribution calculator
Type each value below and press Run. The page prints the quantile and the parameter line it used, so the answer can be checked against the formula rather than taken on trust.
The inputs this page reads are Probability level p (strictly between 0 and 1); Mean μ (any real number); Standard deviation σ (above 0).
The parameterisation
μ is the mean and σ > 0 the standard deviation. The page returns x = μ + σ·Φ⁻¹(p), with p strictly between 0 and 1; at p = 0.5 the answer is μ.
The numeric method
Acklam's rational approximation for the inverse normal, followed by one Halley refinement against the normal CDF, so the printed z agrees with Φ to about 1e-15.
The printed value is accurate to about 1e-15, limited by the double-precision CDF the refinement uses. The page returns the quantile only; it does not also print a test statistic, a p-value or a decision.
What to Expect
Best for
- finding a z critical value from a tail probability
- turning a percentile into the value it cuts off
Not ideal for
- a probability of exactly 0 or 1, which has no finite answer
- a t or chi-square quantile, which uses a different curve
What this tool keeps
- Double-precision arithmetic in your own browser
- The same inputs always produce the same output
Common errors
- A probability of exactly 0 or exactly 1 has no finite quantile, so the page refuses it instead of printing an infinity. σ must be above zero.
Example use cases
- confidence-interval work
- reading a percentile back to a measurement
Sample input
p = 0.975 on the standard normal curve.
Sample output
x with P(X ≤ x) = 0.975 is 1.95996.
Who this is for
- students
- analysts
Frequently asked questions
Which parameterisation does this page use?
μ is the mean and σ > 0 the standard deviation. The page returns x = μ + σ·Φ⁻¹(p), with p strictly between 0 and 1; at p = 0.5 the answer is μ.
How is the result computed?
Acklam's rational approximation for the inverse normal, followed by one Halley refinement against the normal CDF, so the printed z agrees with Φ to about 1e-15. The result is accurate to about 1e-15, limited by the double-precision CDF the refinement uses.
What inputs are refused?
A probability of exactly 0 or exactly 1 has no finite quantile, so the page refuses it instead of printing an infinity. σ must be above zero.
Is anything uploaded?
No. Every number is computed by JavaScript in this page from the values you typed; nothing is posted, stored or logged.
Build custom tools for your store
Join the SDK program to create useful ecommerce utilities for your store.