Z critical value for 98% confidence
The z critical value for 98% confidence is 2.326. It leaves 1% in each tail of the normal curve (α = 0.02, two-tailed).
How to work it out
- 1
The confidence level C is the area in the middle. The rest, α = 1 − C, is split between two tails.
- 2
Find the z-score with 1 − α/2 of the area to its left.
- 3
The confidence interval for a mean with known standard deviation σ is x̄ ± z*·σ/√n, and for a proportion p̂ ± z*·√(p̂(1−p̂)/n).
LaTeX source of the formulas on this page
\[ z^{*}_{98\%} = 2.326 \]
\[ \alpha = 1 - 0.98 = 0.02,\qquad \frac{\alpha}{2} = 0.01 \]
\[ z^{*} = \Phi^{-1}(0.99) = 2.326 \]
\[ \bar{x} \pm z^{*}\frac{\sigma}{\sqrt{n}} \]Margin of error at 98% confidence for σ = 10
| Sample size n | Margin of error |
|---|---|
| 30 | ± 4.247 |
| 100 | ± 2.326 |
| 400 | ± 1.163 |
| 1000 | ± 0.736 |
Critical values for the other levels
| Confidence | Two-tailed z* | One-tailed z |
|---|---|---|
| 80% | 1.282 | 0.842 |
| 85% | 1.440 | 1.036 |
| 90% | 1.645 | 1.282 |
| 95% | 1.960 | 1.645 |
| 98% | 2.326 | 2.054 |
| 99% | 2.576 | 2.326 |
| 99.5% | 2.807 | 2.576 |
| 99.9% | 3.291 | 3.090 |
Questions
What is the critical value for 98% confidence?
z* = 2.326 (two-tailed).
What is alpha for 98% confidence?
α = 0.02, so 1% in each tail.
Do I use z or t for a 98% confidence interval?
Use z* = 2.326 when the population standard deviation is known or the sample is large. With an unknown σ and a small sample use the t critical value for the right degrees of freedom, which is larger.