Chapter 5. Data with Ignorance
The great truth is that we don’t know everything. I have already discussed the need for special values in encoding schemes to allow for missing data, miscellaneous categories, and so forth. But what do you do when the data value is either absurd or missing completely? What if the “exception codes” built into the encoding scheme cannot be used for computations?
Statistics has techniques for replacing bad data with approximations that let us continue on at the aggregate level, even though the individual data might be wrong or at least not verified. The purpose of this chapter is not to be a class in statistics but only to make you aware of their existence. If you don’t understand some of the terms, you can either skip ...
Get Joe Celko's Data, Measurements and Standards in SQL now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
