liveBook · Manning

Cross-sectional data

As explained in Outlier Detection in Python

Cross-sectional data consists of observations on multiple entities without a temporal sequence being the primary organizing dimension.

Cross-sectional data is tabular data organized around multiple entities, where each row represents one entity and time is not the primary organizing dimension. A baseball dataset is cross-sectional when each row describes one player rather than a measurement sequence. section 17.1

Distinguish it from related data structures:

  • Time-series data follows one entity at regular time intervals, commonly with columns for measurement time and value. section 17.1
  • Panel data combines multiple entities with repeated observations over time. section 17.1
  • A date or year column does not make a dataset time series when it records an entity property, such as a player's birth date or debut year. section 17.1

How Outlier Detection in Python covers it

How deep it goes
Defines the structure and distinguishes it from panel and time-series data, stopping short of analytical methods.
Examples
Uses baseball player records containing seasons, games, at-bats, runs, and hits.
What you can do after
Evaluate whether rows represent independent entities or observations arranged as measurements over time.
How it connects
Contrasts cross-sectional data with panel data and time-series data.

Also explained in

Compare how 2 books explain cross-sectional data →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Outlier Detection in Python. The section links point to the parts of the book it draws on.