It is a range around a sample average that is likely to contain the true average for the full population, not just your sample. A 95% confidence interval of $76 to $93 means that if you repeated the same sampling process many times, about 95% of the intervals you calculated would contain the real average.
What is the difference between confidence interval and margin of error?
The margin of error is the plus-or-minus distance from your sample mean, and the confidence interval is the full range that results from adding and subtracting that margin. This calculator shows both, since the margin alone and the two boundary numbers are each useful in different contexts.
Why does a bigger sample size narrow the interval?
A larger sample size reduces the standard error, which is the standard deviation divided by the square root of the sample size. As the sample grows, that division shrinks faster, tightening the interval around the sample mean because more data points reduce the influence of any single unusual observation.
Should I use 90%, 95% or 99% confidence?
95% is the standard default across most marketing and business analytics. Use 99% when a wrong estimate is costly, such as financial planning, since it produces a wider but more certain range. Use 90% when you want a tighter estimate and can tolerate slightly more risk of the true value falling outside it.
Does this work for small sample sizes?
It will calculate a result for any sample size above 1, but the underlying z-distribution approximation is most accurate once your sample size is 30 or more. Below that, a t-distribution technically produces a wider, more conservative interval, which this calculator flags in its note.
Is this the right tool for a conversion rate or survey percentage?
No, use a proportion-based calculator instead, since a percentage like a conversion rate follows different math than a numeric average with a standard deviation. Our margin of error calculator is built specifically for proportions and percentages.