Descriptive statistics provide functions to statistically analyze and explore a Teradata database. Descriptive statistical analysis is valuable for the following reasons:
- It provides business insight.
- It uncovers data quality issues, which, if not corrected or compensated for, jeopardize the accuracy of analytic models based on the data.
- It isolates the data used in building analytic models. For example, when an outlying value is identified, you can include or exclude that value depending on a particular business problem.
- Statistical processes used in analytic modeling require a certain type of data distribution. Descriptive statistical analysis help determine the suitability of various data elements for model input and suggest transformations that may be required.
Descriptive Statistics are performed without the need of the Teradata Warehouse Miner provided the external stored procedure (td_analyze) is installed and the necessary permissions granted.