chapter 6 slater

Data Cleaning

The process of correcting errors and inconsistencies in data to enhance its quality.

Data Structuring

The organization of data into a defined format for analysis, including methods like aggregation and joining.

De-duplication

The method of removing duplicate entries in data while preserving original data integrity.

Data Joining

The process of combining data from various sources to create a comprehensive dataset for analysis.

Data Pivoting

Transforming data from a row-oriented format to a columnar format to ease analysis.

Imputation

The technique of replacing missing data with substitute values, documented for future reference.

Filtering

The act of removing unnecessary or irrelevant data from a dataset.

Consistency

The practice of maintaining uniform data formats and structures across different systems.

Visual Inspection

Manually checking data to identify errors or inconsistencies in a dataset.

Statistical Tests

Using statistical analysis methods to validate the integrity of the data and detect anomalies.

Sample Audit

Examining a subset of data to verify its accuracy and representation of the whole dataset.

Threshold Violations

Situations where data values fall outside accepted numerical ranges and require correction.

Entry Errors

Mistakes made during data input, whether due to human error or system limitations.

Parsing

The process of dividing data into multiple fields by recognizing patterns.

Concatenation

The act of merging multiple fields into a single unit, often for easier identification.

Contradiction Errors

Conflicts that arise when data entries describe the same entity in inconsistent ways.

Attribute Dependencies

Errors that occur when related data points do not align or match accurately.

Handling Cryptic Data Values

Decoding nonsensical data points that require contextual understanding to interpret.