A z score of -1.3 is approximately at the 9.68th percentile in a standard normal distribution, or about the 10th percentile when rounded. In other words, a value with this z score is higher than roughly 9.7% of observations and lower than roughly 90.3%, assuming the data follow a normal distribution.
What a z score of -1.3 means
A z score describes how far a value is from the mean, measured in standard deviations. The formula is z = (x - μ) / σ, where x is the value, μ is the mean, and σ is the standard deviation. A score of -1.3 means the value is 1.3 standard deviations below the mean.
The minus sign indicates direction, not a percentile below zero. Percentiles run from 0 to 100, so a negative z score still corresponds to a positive percentile. Because -1.3 is below the mean, its percentile is below 50. The exact percentile depends on using the standard normal curve as the reference distribution.
How the percentile is calculated
The percentile for a z score is the area under the standard normal curve to its left. Written as a probability, this is Φ(-1.3), where Φ is the cumulative distribution function of a normal distribution with mean 0 and standard deviation 1. A z table or statistical calculator gives approximately 0.0968; multiplying by 100 gives 9.68%.
This is a cumulative percentile, not the percentage of scores that equal -1.3. For a continuous normal distribution, the probability of getting exactly one precise value is effectively zero. The percentile instead describes the share of values at or below that point.
Different tables may display slightly different rounded values. For example, a table that reports four decimal places may show 0.0968, while a chart or classroom answer may round the result to the 10th percentile. Those are consistent approximations, not different interpretations.
Interpreting the result in context
Suppose test scores have a mean of 70 and a standard deviation of 10. A score with z = -1.3 would be 13 points below the mean: 70 + (-1.3 × 10) = 57. If scores are approximately normally distributed, a score of 57 is near the 9.7th percentile. Roughly 10 out of 100 people would score at or below it, and about 90 would score above it.
The percentile does not tell you the practical importance of the score by itself. A low score might matter greatly in a clinical screening or have little consequence in another setting. Interpretation depends on what was measured, how reliable the measure is, the relevant comparison group, and any decision being made from the result.
It also does not mean the person scored 9.7% on a test. Percentile rank and percentage correct are different quantities: the first compares a result with other results, while the second describes the fraction of questions answered correctly or points earned.
Converting between a z score and a raw value
If the mean and standard deviation are known, a z score can be converted back to the original measurement using x = μ + zσ. For example, with a mean of 500 and a standard deviation of 80, z = -1.3 corresponds to 500 - (1.3 × 80) = 396.
This conversion is useful because the z score itself has no original units. A z score of -1.3 could describe a test result, a height measurement, or another quantity; the raw value changes with the scale. The percentile remains about the same only when the standard normal model is an appropriate reference.
How much does -1.3 differ from nearby z scores?
Percentiles are not evenly spaced along the z-score scale. Near the center of the normal curve, a small change in z corresponds to a larger change in percentile than it does far out in a tail, where observations are less common. For orientation:
- z = 0 is the 50th percentile.
- z = -1.0 is about the 15.9th percentile.
- z = -1.3 is about the 9.7th percentile.
- z = -2.0 is about the 2.3rd percentile.
These comparisons help show that -1.3 is below average, but not as far into the lower tail as -2. They are approximate cumulative probabilities under the standard normal model.
When the normal assumption matters
The value 9.68% is exact to the shown precision for the standard normal distribution, but a real dataset may not be normally distributed. If the data are skewed, have unusually heavy tails, contain clusters, or include many tied values, the fraction of observations below a z score of -1.3 may differ from 9.7%.
There is an additional distinction between a theoretical normal percentile and an empirical percentile. A theoretical percentile comes from the normal curve. An empirical percentile is calculated by ranking actual observations in a particular dataset. If you need to interpret a particular person’s standing, use the appropriate reference population and the method specified by the test, study, or analysis. A z score calculated from a sample also carries uncertainty, especially when the sample is small.
Frequently Asked Questions
Is a z score of -1.3 the 10th percentile?
Approximately. Its standard normal percentile is 9.68%, which is commonly rounded to the 10th percentile.
Does a negative z score mean a negative percentile?
No. A negative z score means the value is below the mean. The percentile is the proportion of values below it, so it remains between 0 and 100.
What percentage is above a z score of -1.3?
About 90.32% of a standard normal distribution lies above -1.3, because 100% minus 9.68% is 90.32%.
How do I find the percentile without a z table?
Use a calculator or statistics tool that provides the standard normal cumulative probability, often labeled normal CDF or Φ(z). Enter -1.3 and convert the resulting probability, about 0.0968, to a percentage.
Is the 9.7th percentile the same as a score of 9.7%?
No. A percentile rank compares a value with a reference distribution; a percentage score usually indicates the share of points or items earned.
