Standard errors are similar to standard deviations and describe the precision of the data points. They are used to construct margins of error: the 90% margin of error is the standard error multiplied by 1.645.

Technical definition

The standard error of a data point is a measure of its accuracy, equal to the standard deviation of the distribution of a large population of such data points. It is used to generate confidence intervals of the data points.

Because most data on Metopio is aggregated statistics and rates, the standard errors and confidence intervals are very important in communicating how well we know each data point. The smaller the standard error (or confidence interval), the more confident we are about where the true estimate lies. With large populations, standard errors let us provide good estimates without taking the time and expense to survey every single person.

Glossary of technical terms