Size and Significance in eDiscovery Sampling

Statistics for eDiscovery: Size and Significance in eDiscovery Sampling

How big a sample do we need in eDiscovery?

The required size of a sample depends on the test being run, the desired confidence level, and the desired confidence interval. At reasonable levels, the number of documents that must be reviewed, for example, is often only a few hundred.

What is a statistically significant sample?

The phrase “statistically significant” when referring to sample size is misused. Samples are not statistically significant. The outcome of a statistical test can be statistically significant if it is unlikely to have occurred by chance. When considering sample size, the relevant dimension is called “power.” Basically, power refers to the sample size required to find significant an effect of a certain size.

Does our desired sample size depend on the size of the population/collection?

For all practical purposes in eDiscovery, the size of the collection does not matter, provided that the size of the collection is much larger than the size of the sample.

Source:  Statistics For eDiscovery (PDF) - Used by Permission of Herbert L. Roitblat, Ph.D.

Series:  Statistics for eDiscovery – Blog Posts – Orange Legal Technologies.

Orange Legal Technologies helps corporate legal departments and their outside counsel conduct the critical electronic discovery task of document review by providing advanced predictive coding technologies and expert reviewer assistance to accelerate the electronic discovery process. To learn more about our automated predictive review services, click here.

This entry was posted on Monday, February 27th, 2012 at 2:22 pm. It is filed under metadata, resources and tagged with resources, services. You can follow any responses to this entry through the RSS 2.0 feed.