Custodians, Relevancy and eDiscovery Sampling

Statistics for eDiscovery: Custodians, Relevancy and Sampling

We’ve collected documents from a large number of custodians only some of whom are relevant to the matter at hand. Can we still use sampling?

Sampling, like all statistics, is just a way to tell a story in a principled way. Your sampling frame, the population from which you draw your sample can be anything you want, but you can then talk about the sample as representing the group from which you sampled. If we are dealing with an election poll, we don’t include non-citizens in our poll. If we are trying to predict the Republican primary, we don’t include Democratic party members in our poll.

On the other hand, if you want to make statements about the whole collection, then you have to sample from the whole collection. We cannot say anything reliable about documents that were not included in our sample frame—the collection from which the sample was drawn. People do sometimes pick the wrong custodians, the wrong time frame and the wrong search criteria. It is a judgment call to pick the right population to sample from.

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 Friday, February 17th, 2012 at 9:57 am. 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.