Which data quality dimension relates to missing values in a data set?

• A. Outliers
• B. Validation
• C. Redundancy
• D. Completeness

Answer: (D)

Completeness is the data quality dimension that measures whether all required data are present in the dataset. When values are missing, the data are incomplete, which can bias analyses, reduce statistical power, or make certain computations impossible. For example, missing a key field like customer ID or purchase date can prevent accurate grouping, joining datasets, or calculating metrics. Keeping data complete means capturing and storing all necessary fields for each record, so analyses can be performed on the full set of observations.

To improve completeness, enforce mandatory fields at data entry, implement validation rules that flag missing values, and establish data governance practices to ensure key attributes are collected consistently. When gaps do occur, imputation or data augmentation can be considered, but these methods introduce assumptions and should be used carefully. By focusing on completeness, you ensure that the dataset has enough information to support reliable analysis and decision-making.

Outliers relate to anomalous values, not presence of data. Validation concerns conformance to formats and rules, not whether data are missing. Redundancy deals with duplicate information, not missing values.