The confidence interval for a <span>(1−α)%</span> confidence level is given by
<span> (<span>θ0</span>−<span>Z<span>α/2 </span></span><span>σ/√n</span>, <span>θ0</span>+<span>Z<span>α/2 </span></span><span>σ/√n</span>)
</span><span>θ0</span> is the measured statistic, <span>Z<span>α/2</span></span> is the cutoff/critical value, and <span>σ/<span>√n</span></span> is the standard error. σ is the population standard deviation (if known) or can be estimated by a sample standard deviation. n is the sample size.
The cutoff value depends on the test you wish to use, and <span>θ0</span><span> depends on the statistic you wish to estimate.</span>
