Data Accuracy, Integrity and Bias
Data Accuracy
Accuracy of data means the extent to which it is error free. In other words, if a data has errors in it, it is inaccurate. These errors can be caused and generated at any stage of the system including the gathering of data, the input of data, data being out of date, and the mismatch of data to a person.
An example of inaccurate data could be when entering information for the Schoolies database; a person who is under 18 is entered as being over 18.
Data Integrity
Relating to data, integrity means the reliability of the data. For data to have integrity it has to be accurate. Data integrity is achieved when data passes the ACID test.
The acid test consists of four steps.
Atomicity-
Occurs when all of the steps involved in a transaction are completed successfully as a group. If any step fails, no other step should be completed.
Consistency-
Occurs when a transaction successfully transforms the system and the database from one valid state to another.
Isolation-
Occurs if all the changes that a transaction is processed concurrently with other transactions and still behaves as if it were the only transaction executing the system.
Durability-
Occurs if all the changes that a transaction makes to the database become permanent when the transaction is committed.
Bias in Data
Bias is the straightness of data. If data is skewed then it is biased. Meaning it is controlled to a certain point to give a certain result. For example, a column can be left out of a graph to make another column more noticeable, or the way the data is scaled can distort the overall result.
1 comments:
Integrity of data relates to how reliable it is in terms of timeliness. ie out of date data means the data has no integrity.
Your bias description isn't clear
Post a Comment