Home › Statistics & Probability Calculators › Z Score for 90% Confidence
Z Score for 90% Confidence
For a 90% confidence interval, the critical value is z* = 1.6449 (two-sided; often rounded to 1.645 or 1.64). It is the point of the standard normal curve with 90% of the area between −z* and +z*, leaving α/2 = 0.05 in each tail: z* = Φ⁻¹(1 − α/2), with α = 0.1.
For a one-sided bound at 90% confidence, all of α sits in one tail and the value is 1.2816.
Critical z values for common confidence levels
| Confidence | α | Two-sided z* | One-sided z |
|---|---|---|---|
| 80% | 0.2 | 1.2816 | 0.8416 |
| 85% | 0.15 | 1.4395 | 1.0364 |
| 90% | 0.1 | 1.6449 | 1.2816 |
| 95% | 0.05 | 1.9600 | 1.6449 |
| 98% | 0.02 | 2.3263 | 2.0537 |
| 99% | 0.01 | 2.5758 | 2.3263 |
| 99.5% | 0.005 | 2.8070 | 2.5758 |
| 99.9% | 0.001 | 3.2905 | 3.0902 |
Worked example: margin of error
A sample of n = 50 test scores has mean 78 and a known population standard deviation of 12.
- Standard errorσ ÷ √n = 12 ÷ √50 = 1.6971
- Margin of errorz* × SE = 1.6449 × 1.6971 = 2.791
- 90% confidence interval78 ± 2.791 = (75.21, 80.79)
Small samples: use t instead of z
When the population standard deviation is unknown and the sample is small, use the t distribution with n − 1 degrees of freedom. Its 90% critical values are larger than z* and shrink towards 1.6449 as the sample grows:
| Degrees of freedom | t* for 90% (two-sided) |
|---|---|
| 5 | 2.0150 |
| 10 | 1.8125 |
| 15 | 1.7531 |
| 20 | 1.7247 |
| 30 | 1.6973 |
| 60 | 1.6706 |
| 120 | 1.6577 |
| ∞ (z) | 1.6449 |
Frequently asked questions
- What is the z score for 90% confidence?
- 1.6449 for a two-sided interval, 1.2816 for a one-sided bound.
- Why is the 90% z value 1.645?
- Because 90% of the standard normal distribution lies between −1.645 and +1.645; the remaining 10% is split equally between the two tails.
- When should I use t instead of z?
- Use t when you estimate the standard deviation from the sample, especially with fewer than about 30 observations.
Last reviewed: November 16, 2026. Every figure on this page is calculated from the formulas shown.
