Quantitative & Tabular Data¶

March 2026

Draft

This activity guide is under development. The structure is in place but the content is not yet complete.

What this task involves¶

Many humanities researchers work with tabular data: excavation records, catalogue entries, survey responses, prosopographic databases, bibliographic exports, census data, and statistical evidence. The task involves cleaning, exploring, summarising, and analysing structured data — often as a preliminary step before more formal statistical or database work.

Where AI tools help¶

AI tools with data analysis capabilities (ChatGPT's data analysis, Claude's file handling, Gemini's table support) can perform first-pass exploration of uploaded CSVs and spreadsheets: identifying patterns, anomalies, missing values, and outliers. They can generate charts, pivot tables, summary statistics, and structured queries. For digital humanities researchers, coding assistants can help write scripts for data cleaning, transformation, and analysis.

What to watch out for¶

Models may misinterpret column semantics, apply inappropriate statistical methods, or produce charts that misrepresent the data. Treat AI-generated analysis as exploratory, not as a final statistical workflow. Any quantitative claims that appear in published work must be verified through reproducible methods.

Worked examples¶

Coming soon.