What Is a Z-Score? A Beginner's Guide With Examples
Maya got 82 on her chemistry test. She stared at the number and had no idea if she should be happy or not. 82 out of 100 sounds decent. Then again, what if everyone else got 90?
A z-score answers exactly that question. A z-score tells you how far a value sits from the mean (the average), measured in standard deviations. That's the whole idea. Everything else on this page is just learning to read that number.
The definition, without the jargon
Here's the formula:
z = (x − μ) / σ
Don't let the Greek letters put you off. They stand for ordinary things:
- x is your value — Maya's 82, a baby's weight, a day's temperature.
- μ (mu) is the mean, the average of the whole group.
- σ (sigma) is the standard deviation, a measure of how spread out the group is. Small σ means everyone clustered near the average. Big σ means scores were all over the place.
Subtract the mean from your value and you get the raw gap: how many points above or below average you are. Dividing by σ converts that gap into standard-deviation units, which is what makes z-scores comparable across completely different tests and measurements.
Statisticians also call the z-score a standard score, and that name is honestly the clearest one. It takes any value, from any scale, and restates it on one standard scale where 0 is average.
A worked example, step by step
Back to Maya. Her class results: mean 74, standard deviation 4.
Step 1: subtract the mean. 82 − 74 = 8. She's 8 points above average.
Step 2: divide by the standard deviation. 8 / 4 = 2.00.
Her z-score is +2.00. She didn't just beat the average — she's two full standard deviations above it, which puts her at the 97.72nd percentile. Only about 2 students in 100 scored higher. The 82 that looked so ordinary was one of the best results in the class.
Now the flip side. Another student, Dan, scored 66 in the same class:
66 − 74 = −8, and −8 / 4 = −2.00. Dan is two standard deviations below the mean, at the 2.28th percentile. Same test, same 8-point gap, opposite direction — and the sign of the z-score is what shows it.
If you don't feel like doing this by hand, the z score calculator on our homepage takes the value, mean, and standard deviation and returns the z-score and percentile instantly.
What the sign and size tell you
Two things, that's all:
The sign tells you direction. Positive means above the mean. Negative means below it. Zero means you landed exactly on the average. A negative z-score isn't a mistake or a bad mark — half of every group sits below the mean, so negative z-scores are everywhere. We have a whole post on what a negative z-score means if that still feels off.
The size tells you how unusual the value is. Most values in any roughly bell-shaped dataset land between z = −1 and z = +1. Push past ±2 and you're in unusual territory. Past ±3 and you're looking at something genuinely rare — fewer than 3 in 1,000 values get out there. Our guide to how to interpret z-scores walks through each band with examples.
Why not just use the raw score?
Because raw scores don't travel. An 82 on Maya's chemistry test (mean 74, SD 4) is a z of +2.00. An 82 on an easier test with mean 80 and SD 2 gives z = (82 − 80) / 2 = +1.00. Same number on the page, completely different performance.
That's the practical magic here. SAT sections, height measurements, factory part dimensions — once everything is in z-scores, you can compare them fairly. Colleges, researchers, and quality-control teams lean on this constantly. (And if you're wondering how z-scores relate to the percentile on a report card, that's covered in z-score vs percentile.)
One honest caveat before you go: z-scores assume your data is at least roughly bell-shaped. For wildly skewed data — household incomes are the classic case — a z-score still computes, but it describes the shape poorly. Check the shape of your data first. For exam scores, heights, temperatures, and most classroom or lab measurements, you're on safe ground.
Want the calculation broken down even further? The z score formula page goes piece by piece, and the z score to percentile calculator converts any z you already have.
Frequently asked questions
What does a z-score of 1 mean?
A z-score of 1 means the value sits exactly one standard deviation above the mean. On a test, that's a clearly above-average result — it lands at about the 84.13th percentile, so it beats roughly 84 out of every 100 scores in the group. It's a strong result, but not a rare one.
Is a higher z-score always better?
No. A higher z-score just means further above the average. That's good for an exam score, but in sprinting or golf the low scores win, so a negative z-score is the one athletes want. The number tells you position, not quality — you always need context to judge whether that position is desirable.
What is the range of z-score values?
There's no fixed limit, but in practice most z-scores fall between −3 and +3, because 99.7% of values in a normal distribution sit within three standard deviations of the mean. A z-score of +4 or −4 is possible, yet it happens so rarely that it's worth double-checking the data before believing it.
What three numbers do I need to calculate a z-score?
You need the value itself (x), the mean of the group (μ), and the standard deviation (σ). Subtract the mean from the value, then divide by the standard deviation. If you don't know the mean or standard deviation for your set of scores, you can't get an exact z-score.