This table gives the area under the standard normal curve to the left of a z-score, which is the proportion of values that fall below it. Type a z-score into the box above and press Look up. The matching cell is highlighted, and you also get the right-tail area, the area between −z and z, and the two-tailed p-value, so you don’t have to do the subtraction by hand.
How to read the z table
Split your z-score into two parts. The first decimal place picks the row and the second decimal place picks the column. For z = 1.27, go down to the row marked 1.2, then across to the column marked .07. The number there is 0.89796, so about 89.8% of a normal distribution lies below z = 1.27. Show me z = 1.27 in the table.
Negative z-scores work the same way on the negative table. For z = −1.27 you read row −1.2, column −.07, and get 0.10204. That is the same as 1 − 0.89796, because the normal curve is symmetric. Show me z = −1.27.
Turning the table value into the answer you need
The table only ever gives you one thing: the area to the left. Almost every question can be answered from that one number.
| You want | Do this | Example with z = 1.27 |
|---|---|---|
| Proportion below z | Read the table | 0.89796 |
| Proportion above z | 1 − table value | 1 − 0.89796 = 0.10204 |
| Proportion between −z and z | Table value at z − table value at −z | 0.89796 − 0.10204 = 0.79592 |
| Two-tailed p-value | 2 × (area beyond |z|) | 2 × 0.10204 = 0.20408 |
To find the area between two different z-scores, look up both and subtract the smaller from the larger. Between z = 0.5 and z = 1.5: 0.93319 − 0.69146 = 0.24173, so about 24% of values sit in that band.
A worked example with real numbers
Scores on a test have a mean of 70 and a standard deviation of 8. What share of students scored below 80?
- Convert the score to a z-score: z = (80 − 70) / 8 = 1.25.
- Find row 1.2, column .05: 0.89435.
- So about 89.4% of students scored below 80, and 10.6% scored above.
If you would rather skip the conversion, the z-score calculator does step 1 and the normal distribution calculator takes the raw score, mean and SD directly.
Reading the table backwards: from a percentile to z
Sometimes you know the area and need the z-score, for example to find the cutoff for the top 5%. Look for 0.95000 in the body of the table. It falls between 0.94950 (z = 1.64) and 0.95053 (z = 1.65), so the cutoff is about 1.645. When the number you want sits between two cells, pick the closer one or split the difference. For an exact answer, use the inverse normal calculator.
z values worth memorising
| Confidence level | Two-tailed α | Critical z |
|---|---|---|
| 90% | 0.10 | 1.645 |
| 95% | 0.05 | 1.960 |
| 99% | 0.01 | 2.576 |
| 99.9% | 0.001 | 3.291 |
The 68-95-99.7 rule comes from the same table: 68.27% of values lie within 1 SD of the mean, 95.45% within 2 SD and 99.73% within 3 SD.
Mistakes that cost marks
- Reporting the left area when the question asks for “more than”. If the question says above, greater than or at least, subtract from 1.
- Using the positive table for a negative z. A z of −0.84 gives 0.20045, not 0.79955. If your answer for a negative z is bigger than 0.5, something went wrong.
- Forgetting to double for a two-tailed test. The one-tail area for z = 2.1 is 0.01786. The two-tailed p-value is 0.03573.
- Using z when σ is unknown. If you estimated the standard deviation from a small sample, the t table is the right one.
Check yourself
What proportion of a normal distribution lies above z = 2.10?
The table gives 0.98214 to the left of 2.10, so the area above is 1 − 0.98214 = 0.01786, or about 1.8%.
Heights have mean 170 cm and SD 10 cm. What share of people are between 160 and 180 cm?
Those are z = −1 and z = 1. The table gives 0.84134 and 0.15866, and the difference is 0.68269, so about 68%.
Which z-score marks the bottom 20%?
Look for 0.20000 in the negative table. The closest cell is 0.20045 at z = −0.84, so the cutoff is about z = −0.84.