Skip navigation

“Raw Data” Is An Oxymoron¬†talks about Big Data being applied to different disciplines:

“Every discipline and disciplinary institution has its own norms and standards for the imagination of data, just as every field has its accepted methodologies and its evolved structures of practice” (3).

As a data scientist working in data analytics with respect to online education, I can relate to this statement. At work, I construct systems and algorithms that condense real world data into a standardized data object, which interacts with other objects in data structures. In the case of online education, I need to structure data relating to students answering questions online into discretized objects respresenting item responses.

While doing so, I need to make sure that what I’m building is consistent with learning theory. I read literature written by non-statisticians and build data models that are analogous to this models presented in this literature; because online education data analytics is such a new field, there is no norm to follow. How raw responses are transformed into structured data – how data is imagined – becomes extremely important to how we do statistical inference.