Descriptive Statistics

Research

Summarising data with measures of centre (mean, median, mode) and spread (SD, IQR) — with EDA and kernel density estimation at higher levels; the precursor to all inferential modelling.

Sources

1. NIST/SEMATECH e-Handbook of Statistical Methods — 1.3.5 Quantitative Techniques itl.nist.gov accessed 22 September 2026
2. NIST/SEMATECH e-Handbook of Statistical Methods — 1.1.1 What is EDA? itl.nist.gov accessed 22 September 2026

The NIST/SEMATECH e-Handbook of Statistical Methods — a US government reference — groups these summaries as measures of location and measures of scale, noting that “the most commonly used measure of location is the mean”, defined as “the sum of all the members of the given population divided by the number of members in the population”. On the exploratory side it describes EDA as “an approach/philosophy for data analysis that employs a variety of techniques (mostly graphical) to maximize insight into a data set”, one that lets “the data itself to reveal its underlying structure” rather than assuming a model first.

This entry is sourced to a body with standing over the practice it names, which is tier 1 of this lexicon’s rule for research terms. Where a definition is quoted, it is the body’s own wording; the reading of what it implies is this lexicon’s.

Related terms

• Abbreviation
• Abstract
• Abstraction
• Academic Database
• Analysis
• Annotation

From the AJG lexicon archive (July 2026).