Which of the following steps should be taken to ensure data consistency?

While reviewing survey data, an analyst notices respondents entered “Jan,” “January,” and “01” as responses for the month of January.

Which of the following steps should be taken to ensure data consistency?
A . Delete any of the responses that do not have “January” written out.
B . Replace any of the responses that have “01”.
C . Filter on any of the responses that do not say “January” and update them to “January”.
D . Sort any of the responses that say “Jan” and update them to “01”.

View Answer

Answer: C

Explanation:

Filter on any of the responses that do not say “January” and update them to “January”. This is because filtering and updating are data cleansing techniques that can be used to ensure data consistency, which means that the data is uniform and follows a standard format. By filtering on any of the responses that do not say “January” and updating them to “January”, the analyst can make sure that all the responses for the month of January are written in the same way. The other steps are not appropriate for ensuring data consistency.

Here is why:

Deleting any of the responses that do not have “January” written out would result in data loss, which means that some information would be missing from the data set. This could affect the accuracy and reliability of the analysis.

Replacing any of the responses that have “01” would not solve the problem of data inconsistency, because there would still be two different ways of writing the month of January: “Jan” and “January”. This could cause confusion and errors in the analysis.

Sorting any of the responses that say “Jan” and updating them to “01” would also not solve the problem of data inconsistency, because there would still be two different ways of writing the month of January: “01” and “January”. This could also cause confusion and errors in the analysis.