3.2.1 Definitions and Formulas

Pivot Table
An Excel tool for allowing you to quickly cross-section and summarize your data. Values can be displayed as means, counts, sums, and standard deviations, percentages (of rows, columns, or totals). The data can be cross-sectioned in up to three variables simultaneously (row, column, and page) and variable ranges can be grouped for easier display.
reshapeGUI
An R package for cross-sectioning data the same way as a Pivot Table in Excel.
Cross-sectioning data
Term used to refer to taking the data and breaking it down into categories and reporting on each category separately.
Data Mining
Process of combing through data, using a variety of tools, such as pivot tables, to find information about the underlying source of the data. For example, companies mine the data on past customer purchases in order to develop targeted advertising and marketing campaigns that address the tendencies of certain types of customers.
Field
In a pivot table (or a database) the variables are called fields.
Record
In a pivot table (or a database) the observations are called records.
Raw data
The raw data is all of the data collected, organized for later analysis, with with one observation per row.