An official website of the United States government, Department of Justice.

Confidence Intervals

In a statistical context, populations are defined by parameters such as mean and variance. These parameters are estimated from the data obtained from population samples. Here we are interested in the frequency of an allele in the population, estimated from its proportion in the sample set. As the sample size increases, the estimate will become a more dependable measure of the true frequency of the allele in the population.10 Classical statistics deals with the relationship between sample size and the reliability of a parameter estimate by calculating a confidence interval, which furnishes a range of plausible values for the unknown parameter.

Confidence Interval

z√[p(1-p)]/n

Where z is found from statistical tables and depends on the desired range (e.g. 95%); and p is the proportion observed in the sample of size n

Watch a video on confidence intervals presented by Greggory LaBerge.

Watch a video on estimation presented by Greggory LaBerge.