Which statement best describes data cleaning in the context of the Large Data Set?

Which statement best describes data cleaning in the context of the Large Data Set?

• A. It increases the dataset size.
• B. It converts all data to a single format.
• C. It removes or corrects inaccurate, inconsistent, or duplicate records before analysis.
• D. It eliminates the need for validation.

Answer: (C)

Data cleaning focuses on improving data quality so analyses are trustworthy. It involves finding and fixing or removing records that are wrong, inconsistent, or duplicated. By cleaning data before you analyse it, you reduce errors that could mislead results and you rely on more accurate summaries and models. In the Large Data Set context, this means checking for mistakes, standardising formats where needed, removing duplicates, and addressing missing or inconsistent values so the dataset reflects reality as closely as possible. The idea that cleaning increases the dataset size isn’t correct, since it often involves removing faulty records. While standardising formats can be part of the process, the main aim is not just formatting but ensuring accuracy and consistency. It also doesn’t eliminate the need for validation—data cleaning is part of validating data, but you still need ongoing checks to ensure data quality throughout analysis.

Data cleaning focuses on improving data quality so analyses are trustworthy. It involves finding and fixing or removing records that are wrong, inconsistent, or duplicated. By cleaning data before you analyse it, you reduce errors that could mislead results and you rely on more accurate summaries and models. In the Large Data Set context, this means checking for mistakes, standardising formats where needed, removing duplicates, and addressing missing or inconsistent values so the dataset reflects reality as closely as possible.

The idea that cleaning increases the dataset size isn’t correct, since it often involves removing faulty records. While standardising formats can be part of the process, the main aim is not just formatting but ensuring accuracy and consistency. It also doesn’t eliminate the need for validation—data cleaning is part of validating data, but you still need ongoing checks to ensure data quality throughout analysis.