A Z value calculator for a normal distribution works out how many standard deviations a given data point (x) is from the mean (μ) of that distribution. You enter the raw score, the mean, and the standard deviation; the calculator returns the Z-score, which tells you exactly how far and in which direction that score sits relative to the average. From the Z-score you can also find the probability of a value falling above or below it, using the standard normal table or a cumulative probability function.
Formula
The Z-score is defined by the formula:
Z = (x − μ) / σ
- x = the raw score or observed data point (same units as the data)
- μ = the mean (average) of the distribution (same units as the data)
- σ = the standard deviation of the distribution (same units as the data)
The result Z is a dimensionless number. A positive Z means the score is above the mean; a negative Z means it is below. The magnitude tells you how many standard deviations away it is. For example, Z = 1.5 means the score is 1.5 standard deviations above the mean.
To convert a Z-score to a probability, we use the cumulative distribution function (CDF) of the standard normal distribution, denoted Φ(Z). There is no simple closed-form formula, but it can be expressed using the error function (erf):
Φ(Z) = 0.5 × [1 + erf(Z / √2)]
This gives the probability that a value drawn from a standard normal distribution is less than Z. In the calculator, that is the “Probability below” output. The probability above is simply 1 − Φ(Z).
Worked Example
Suppose you have a dataset with mean μ = 75 and standard deviation σ = 10. You want to know the Z-score for a raw score of x = 85.
- Subtract the mean from the raw score: 85 − 75 = 10.
- Divide by the standard deviation: 10 / 10 = 1.0.
- The Z-score is 1.0.
- Now find the probability below: Φ(1.0) = 0.5 × [1 + erf(1.0 / √2)] ≈ 0.5 × [1 + erf(0.7071)] ≈ 0.5 × [1 + 0.6827] = 0.8413.
- The probability above is 1 − 0.8413 = 0.1587.
So a score of 85 is 1 standard deviation above the mean, and about 84.13% of the data falls below it, while 15.87% falls above. The calculator gives the same values: Z = 1.0, p_below = 0.8413, p_above = 0.1587.
Assumptions
- The data follows a normal (Gaussian) distribution.
- The mean and standard deviation are known (or accurately estimated from a large sample).
- The standard deviation is positive (σ > 0).
- The distribution is continuous, so probabilities are interpreted as areas under the curve.
When to Use a Z-Score
Z-scores are used in statistics to standardize data from different normal distributions, making them comparable. Common applications include:
- Comparing scores from different tests: If one test has a mean of 70 and SD of 5, and another has a mean of 80 and SD of 10, a raw score of 75 on the first test (Z = 1.0) is relatively higher than a raw score of 85 on the second (Z = 0.5).
- Identifying outliers: In a normal distribution, about 95% of data lies within 2 standard deviations of the mean, and 99.7% within 3. Values with |Z| > 3 are often considered unusual.
- Probability calculations: Finding the proportion of a population that falls above or below a certain threshold (e.g., what percentage of students score above 90?).
- Quality control: In manufacturing, Z-scores help determine how many standard deviations a measurement is from a target specification.
How to Read the Results
The Z-score itself tells you the distance from the mean in standard deviation units. The probability below (p_below) is the area under the normal curve to the left of your raw score. For example, if p_below = 0.95, then 95% of the data is less than your value, and 5% is greater. This is often used to find percentiles: a Z-score of 1.645 corresponds to the 95th percentile (since Φ(1.645) ≈ 0.95).
Remember that the standard normal distribution has a mean of 0 and a standard deviation of 1. The Z-score transforms any normal distribution to this standard form, which is why tables and calculators only need one set of values.
Common Mistakes and Misconceptions
- Using sample standard deviation vs. population standard deviation: The formula assumes you know the true population σ. If you only have a sample, you should use the sample standard deviation (s) as an estimate, but the resulting Z-score is then a t-statistic if the sample is small. For large samples (n > 30), the difference is negligible.
- Mixing up Z-score and t-score: Z-scores are for when σ is known; t-scores are for when σ is unknown and estimated from the sample. In practice, t-scores are more common for small samples.
- Forgetting to check normality: The Z-score itself can be computed for any data, but the probability interpretation is only valid if the underlying distribution is approximately normal. For skewed data, the percentiles may be misleading.
- Rounding too early: In the worked example, if you round Z to 1.0 and then look up Φ(1.0), you get 0.8413. But if you had Z = 0.96, rounding to 1.0 would give a slightly different probability. Always keep enough decimal places in intermediate steps.
Limitations of the Z-Score
The Z-score is a linear transformation, so it preserves the shape of the distribution. However, it does not make a non-normal distribution normal. If your data is heavily skewed, the Z-score will still be skewed, and the probability calculations will be inaccurate. Also, the Z-score assumes the mean and standard deviation are meaningful measures of center and spread, which they are only for symmetric, unimodal distributions. For data with outliers, the median and interquartile range might be more appropriate.
Another limitation: the Z-score is unbounded. There is no maximum or minimum Z-score, but in practice, values beyond ±4 are extremely rare (probability less than 0.0001). The calculator allows any raw score, but if you enter a value far outside the range of the data, the probability will be extremely close to 0 or 1, which might be less informative.
Alternatives to the Z-Score
If your data is not normally distributed, you might consider:
- Percentile ranks: The percentage of data below a given value, which does not require normality.
- T-scores: Used when σ is unknown, especially for small samples. The t-distribution has heavier tails, so the probabilities differ for small degrees of freedom.
- Standardized residuals: In regression, residuals divided by their standard error, to detect outliers.
- Chebyshev’s inequality: For any distribution, at least 1 − 1/k² of data lies within k standard deviations of the mean. This is a conservative bound that works even for non-normal data.
Frequently Asked Questions
What does a Z-score of 2 mean?
A Z-score of 2 means the raw score is exactly 2 standard deviations above the mean. In a normal distribution, about 97.72% of the data falls below this value, and 2.28% falls above. It is often used as a threshold for statistical significance in hypothesis testing (two-tailed).
How do I find the probability from a Z-score without a calculator?
You can use a standard normal distribution table (Z-table), which lists Φ(Z) for positive Z values. For negative Z, use symmetry: Φ(−Z) = 1 − Φ(Z). Find the row for the first two digits of Z and the column for the second decimal place, then read the cumulative probability. For example, Z = 1.23: row 1.2, column 0.03 gives 0.8907.
What is the difference between a Z-score and a standard deviation?
Standard deviation (σ) is a measure of the spread of the data, expressed in the same units as the data. A Z-score is a dimensionless number that tells how many standard deviations a particular value is from the mean. In other words, Z = (x − μ)/σ, so the Z-score is the distance from the mean measured in units of σ.
Can I use a Z-score for non-normal data?
You can compute the Z-score for any data point, but the interpretation as a probability (e.g., 95% within 2σ) only holds for normal distributions. For non-normal data, the Z-score is still a measure of relative position, but you cannot use the standard normal table to find percentiles. Instead, use empirical percentiles from the data.
What is the Z-score for the 95th percentile?
The Z-score that corresponds to the 95th percentile is approximately 1.645. This means that 95% of the data in a normal distribution lies below a value that is 1.645 standard deviations above the mean. This value is commonly used in confidence intervals and hypothesis testing.
How do I calculate the Z-score in Excel?
In Excel, you can use the formula =(x - mean)/stdev to get the Z-score. To find the cumulative probability, use NORM.S.DIST(Z, TRUE) for the probability below, or NORM.DIST(x, mean, stdev, TRUE) directly. For the probability above, subtract from 1.
Related
Formula used
in x | Raw score (x) | - | 85 | -1000 in m | Mean (μ) | - | 75 | -1000 in s | Standard deviation (σ) | - | 10 | 0.001 out z | Z-score | - | (x - m) / s | 4 out p_below | Probability below (P(X < x)) | - | 0.5 * (1 + erf(z / sqrt(2))) | 4 out p_above | Probability above (P(X > x)) | - | 1 - p_below | 4
Each line is one input (in, sel, list) or one result (out: label, unit, formula, decimals). How the calculators work
Method: the standard formula for this calculation with the constants and conversion factors written on the page, rounded as each result states. See method and constants, the disclaimer or report an error.
More in this section
- Normality to g/L Converter & Formula29.220 g/L
- Normality to meq/mL Conversion Calculator1.0000 meq/mL
- Normality Test Q-Q Plot: How to Read It
- Normality Test Results: How to Analyze Them
- Normality Slay the Spire?
- Normality Test for Paired t Test: How to Check