Discussion in 'Data Sets and Feeds' started by Corso482, Feb 16, 2003.
Not sure if you meant this to be in the Retail Firm section, but if you are refering to system testing, out of sample data is data that you test your system on that was not part of the original data set used to create/optimize the system. The idea is that your system will not be biased by data that it has never seen and therefore the results of the system on this "new" data will be more reliable and reduces the likelihood of curve-fitting.
EDIT: Oops, didn't see the other thread you started....I see Hillbilly took care of your question.
Separate names with a comma.