Z Score: Measuring How Unusual a Value Is

Imagine you're in a class of 100 students. The test average is 60 out of 100. You scored 75. That's 15 marks above average — good. But what if the class average was 60 and the standard deviation was only 2? Then almost everyone scored between 54 and 66. Your 75 would be extraordinary — you'd be miles ahead of everyone else.

Now imagine the same average of 60, but the standard deviation is 20. Now scores range from roughly 0 to 120. Your 75 is still above average, but it's not remarkable — many students scored higher.

The Z score captures exactly this: how many standard deviations a value is from the mean. It tells you not just "how far" but "how far relative to the spread."

The Intuition in One Sentence

A Z score answers: "If the average is the center of the data, and the standard deviation is the typical distance from that center, then my value is ___ typical distances away."

• Z = 0 → exactly at the mean.
• Z = +1 → one standard deviation above the mean.
• Z = -2 → two standard deviations below the mean.

The bigger the absolute Z score, the more unusual the value.

The Precise Formula

Where:

• $x$ = the raw value (your score, height, weight, etc.)
• $\mu$ (mu) = the population mean
• $\sigma$ (sigma) = the population standard deviation

If you're working with a sample rather than a population, use the sample mean $\bar{x}$ and sample standard deviation $s$:

Worked Example

A class has test scores with mean $\mu = 70$ and standard deviation $\sigma = 8$.

Student A scores 86.

Student A is 2 standard deviations above the mean. That's quite high — in a normal distribution, only about 2.5% of students score higher.

Student B scores 62.

Student B is 1 standard deviation below the mean. That's below average but not extreme — about 16% of students score lower.

What Z Scores Are Used For

1. Comparing across different scales. If you scored 85 in Physics (mean 70, SD 10) and 72 in Chemistry (mean 65, SD 4), which is better relative to the class? Physics Z = 1.5, Chemistry Z = 1.75 — Chemistry is actually the stronger performance.

2. Identifying outliers. In many fields, a value with $|Z| > 3$ is considered an outlier — it's more than 3 standard deviations from the mean.

3. Standardizing data. Many statistical methods (like regression, PCA) assume variables are on a comparable scale. Converting to Z scores (called standardization or normalization) puts everything in the same units: standard deviations.

The Big Picture

The Z score is a universal ruler. It lets you compare any value to its group, regardless of the original units. Whether you're looking at exam marks, heights, stock returns, or blood pressure, the Z score tells you the same thing: how exceptional is this value?