How are confidence intervals calculated?
Confidence intervals are calculated based on the standard error of a measurement. For sample surveys, such as the presidential telephone poll, the standard error is a calculation which shows how well the poll (sample point estimate) can be used to approximate the true value (population parameter), i.e. how many of the people surveyed said they would vote for Dole versus how many people actually would vote for Dole in the election. Generally, the larger the number of measurements made (people surveyed), the smaller the standard error and narrower the resulting confidence intervals. Once the standard error is calculated, the confidence interval is determined by multiplying the standard error by a constant that reflects the level of significance desired, based on the normal distribution. The constant for 95 percent confidence intervals is 1.96.
