Normal distributions are symmetrical, bell-shaped distributions that are useful in describing real-world data. The standard normal distribution, represented by Z, is the normal distribution having a mean of 0 and a standard deviation of 1.
Main article: Standard normal deviate
If X is a random variable from a normal distribution with mean μ and standard deviation σ, its Z-score may be calculated from X by subtracting μ and dividing by the standard deviation:
If X ¯ {\displaystyle {\overline {X}}} is the mean of a sample of size n from some population in which the mean is μ and the standard deviation is σ, the standard error is σ n : {\displaystyle {\tfrac {\sigma }{\sqrt {n}}}:}
If ∑ X {\textstyle \sum X} is the total of a sample of size n from some population in which the mean is μ and the standard deviation is σ, the expected total is nμ and the standard error is σ n : {\displaystyle \sigma {\sqrt {n}}:}
Z tables are typically composed as follows:
Example: To find 0.69, one would look down the rows to find 0.6 and then across the columns to 0.09 which would yield a probability of 0.25490 for a cumulative from mean table or 0.75490 from a cumulative table.
To find a negative value such as –0.83, one could use a cumulative table for negative z-values3 which yield a probability of 0.20327.
But since the normal distribution curve is symmetrical, probabilities for only positive values of Z are typically given. The user might have to use a complementary operation on the absolute value of Z, as in the example below.
Z tables use at least three different conventions:
This table gives a probability that a statistic is between minus infinity and Z.
The values are calculated using the cumulative distribution function of a standard normal distribution with mean of zero and standard deviation of one, usually denoted with the capital Greek letter Φ {\displaystyle \Phi } (phi), is the integral
Φ {\displaystyle \Phi } (z) is related to the error function, or erf(z).
Note that for z = 1, 2, 3, one obtains (after multiplying by 2 to account for the [−z,z] interval) the results f (z) = 0.6827, 0.9545, 0.9974, characteristic of the 68–95–99.7 rule.
This table gives a probability that a statistic is less than Z (i.e. between negative infinity and Z).
4
This table gives a probability that a statistic is greater than Z. : f ( z ) = 1 − Φ ( z ) {\displaystyle f(z)=1-\Phi (z)}
5 This table gives a probability that a statistic is greater than Z, for large integer Z values.
A professor's exam scores are approximately distributed normally with mean 80 and standard deviation 5. Only a cumulative from mean table is available.
"Z Table. History of Z Table. Z Score". Retrieved 21 December 2018. https://www.ztable.net/ ↩
Larson, Ron; Farber, Elizabeth (2004). Elementary Statistics: Picturing the World. 清华大学出版社. p. 214. ISBN 7-302-09723-2. 7-302-09723-2 ↩
"How to use a Z Table". ztable.io. Retrieved 9 January 2023. https://ztable.io/ ↩
0.5 + each value in Cumulative from mean table ↩
0.5 − each value in Cumulative from mean (0 to Z) table ↩