Z-Score Calculator
Standardise every value in a pasted column and read its two-tailed tail probability.
What this page computes
Paste one number per line. The page prints the mean and the sample standard deviation s with the n − 1 divisor, then z = (x − x̄)/s for each value, with its line number and the two-tailed tail probability 2(1 − Phi(|z|)). It closes with how many values sit at least two standard deviations from the mean. The per-value list shows the first forty rows and says how many follow. Figures print to six significant figures.
The z-score is only as meaningful as the column it came from: it rescales the data and assumes nothing about shape, but a z of 2 is not a p-value about the population. A constant column is refused, because s would be zero.
The column stays in the browser and the same values always standardise to the same z-scores.
The page standardises every value in a pasted column: z = (x − mean)/s, with s using the n − 1 divisor, and prints a two-tailed tail probability 2(1 − Φ(|z|)) beside each z. For the eight values 2, 4, 4, 4, 5, 5, 7, 9 the mean is 5 and s is 2.13809, so the 9 becomes z = 1.87083 with p = 0.0613688. It refuses a column where every value is identical, because s is zero and every z would divide by zero.
Standardise a whole column at once, with each value’s z-score and two-tailed tail probability.
How to use it
Paste your data with one value per line; a comma inside a line is refused because this page reads a column. The first forty values are listed with their line numbers and the rest are summarised, so a long paste does not flood the page while nothing is silently dropped from the count.
The divisor, and which tail the probability is
The standard deviation is the sample one, with the n − 1 divisor, which is why the page prints s and n beside the mean: a z-score is only meaningful against the spread it was computed from. The probability is the two-tailed tail 2(1 − Φ(|z|)), so a z of 1.87 is read as the chance of being at least that far from the mean in either direction, not the one-sided chance of being above it. The count of values at |z| ≥ 2 is printed at the end as a quick check of how much of the column sits far out.
What to Expect
Best for
- Standardising a column and spotting values far from the mean
What this tool keeps
- Nothing leaves this tab: the arithmetic runs in the page you are reading, and a reload discards both the input and the result.
Sample input
2 4 4 4 5 5 7 9
Sample output
mean = 5, s = 2.13809, n = 8 z = (x − mean)/s, two-tailed tail probability 2(1 − Φ(|z|)): line 1: 2 → z = -1.40312, p = 0.160581 line 2: 4 → z = -0.467707, p = 0.639994 line 3: 4 → z = -0.467707, p = 0.639994 line 4: 4 → z = -0.467707, p = 0.639994 line 5: 5 → z = 0, p = 1 line 6: 5 → z = 0, p = 1 line 7: 7 → z = 0.935414, p = 0.349575 line 8: 9 → z = 1.87083, p = 0.0613688 |z| ≥ 2: 0 of 8 values
Frequently asked questions
Which standard deviation is used?
The sample one, with the n − 1 divisor — 2.13809 for these eight values. The printed mean and s let each z-score be checked by hand.
Is the probability one-tailed or two-tailed?
Two-tailed: 2(1 − Φ(|z|)), the chance of being at least |z| away from the mean in either direction. A z of 1.87083 gives p = 0.0613688.
Is my data uploaded?
No. Every z-score and its probability are computed in this page from the pasted column, and nothing is posted to a server or stored.
Build custom tools for your store
Join the SDK program to create useful ecommerce utilities for your store.