What does "Estimator" mean?

Definition of Estimator in the context of A/B testing (online controlled experiments).

What is an Estimator?

An estimator is a statistic used for the purpose of estimating an unknown parameter. An estimator is a function of the data in a sample. Common estimators are the sample mean and sample variance which are used to estimate the unknown population mean and variance.

There are two types of estimators: point and interval estimators. A point estimator yield a single value while an interval estimator outputs a set of plausible values. In A/B testing one is most likely to encounter a confidence interval and a maximum likelihood estimate.

All good estimators possess certain desirable properties that make them useful but since some of these properties come with stricter assumption one is always seeking to balance the good properties of an estimator with how tight the estimator premises are. More on the desirable estimator properties can be seen in these entries: efficient estimator, unbiased estimator, consistent estimator, sufficient estimator.

Like this glossary entry? For an in-depth and comprehensive reading on A/B testing stats, check out the book "Statistical Methods in Online A/B Testing" by the author of this glossary, Georgi Georgiev.

Purchase Statistical Methods in Online A/B Testing

Glossary Index by Letter


Select a letter to see all A/B testing terms starting with that letter or visit the Glossary homepage to see all.