Data Quality

How do you determine data quality? One way is to use the 6 data dimensions to see how your data measures up.

Before you can obtain accurate data in the future, you must first understand what you can do now to improve the accuracy of your data. Data validity is a good starting point. We refer to this as syntactic accuracy, looking at the syntax and determining if it’s accurate.

Example of syntactic accuracy: DOB cannot be later than present day

As your project progresses through the 6 data dimensions, you will end up at the last dimension, Accuracy. Ideally, you should aim to achieve semantic accuracy in this last step.

Example of semantic accuracy: A vehicle classified as a “bicycle” should not have eight wheels in a given dataset