The Data

View at publisher Summarise with VIRAT
Authors: David J. Hand
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Data are facts, most often numbers and what those numbers mean – the metadata. Data can be seen as representations of things in the real world, and as simplifications, abstractions, and projections from the world. Data are used to gain understanding and to guide decisions. Data quality is critical, and various questions should be asked before undertaking any analysis, including about how the data were collected, what processing it has already undergone, whether it met any assumptions made by the tools to be used, and whether there are regulatory constraints on how it can be used. Data are generated by measuring or observing (and recording) something about the objects being studied. Representational measurement maps objects and their relationships to a set of numbers which have the same relationships. Pragmatic measurement defines the property being measured in terms of the measurement procedure, so that the measurement is useful for some purpose. Many measurement procedures sit somewhere between these extremes. Numerical values may be transformed, but transformations must yield numbers which preserve any relationships between objects. Transformations made for statistical purposes must be made with care lest they corrupt the representation of the relationships and invalidate any conclusions.

Fields of Study & Subjects

Data Quality and Management Statistical Methods and Applications Research Data Management Practices

Publication details

Journal / source
Chapman & Hall/CRC eBooks
Pages
21–40
Publication date
27 March 2026
Language
EN
Document type
Book chapter