Statistics for eDiscovery: Random Sample Generation and eDiscovery
How do I generate a random sample?
In election polling, it is quite a challenge to generate a truly unbiased random sample. Not everyone who will vote has a telephone, not everyone is willing to answer, not everyone is truthful. Sampling documents is a little easier, because they don’t have a choice in whether they respond or not. The most practical way to generate a random sample is to use a random number generator. Spreadsheet programs, such as Excel, have random number generators built in. If you have, say ten thousand documents, from which you want a sample of 400, then you could generate 400 random numbers in the interval of 1 to 10,000. You need to be careful to prevent the same number appearing twice. Technically, the numbers generated by a random number generator are pseudo- random numbers, but for our purposes, they are good enough. They are pseudo-random in that eventually they will repeat, but unless you are dealing with extremely large samples, the repetition is unlikely to be encountered. These pseudo-random number generators are used in practically all slot machines, for example.
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 24th, 2012 at 12:29 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.
Comments are closed.
The OneO® Discovery Platform is an integrated, web-accessible, forensically sound electronic discovery platform that enables online analytics, processing, and review of data from the security of a hosted centralized repository.
To learn more about how OneO® can allow you to gain full control of the electronic discovery process, click here.
OrangeLT™ Forensics and Collection Services can help you rapidly and accurately acquire potentially relevant electronically stored information (ESI), for audits, investigations, and litigation.
To learn more about how our forensics and collection experts can help you to gain full control of the electronic discovery process, click here.
OneO® Mobile Access provides eDiscovery professionals fast, secure, and convenient access to the full functionality of the OneO® Discovery Platform directly from today's most popular mobile computing devices.
To learn more about how OneO® Mobile Access can help you to gain full control of the electronic discovery process, click here.
Unfiltered Orange Weekly is a weekly news update providing legal professionals with quick reference to unfiltered electronic discovery news, views, and events.
To check out the latest weekly update, click here.
To sign up for our weekly updates, click here.
