The problem with composite indicators.
View / Open Files
Publication Date
2019-04Journal Title
BMJ quality & safety
ISSN
2044-5415
Publisher
BMJ
Volume
28
Issue
4
Pages
338-344
Language
eng
Type
Article
Physical Medium
Print-Electronic
Metadata
Show full item recordCitation
Barclay, M., Dixon-Woods, M., & Lyratzopoulos, G. (2019). The problem with composite indicators.. BMJ quality & safety, 28 (4), 338-344. https://doi.org/10.1136/bmjqs-2018-007798
Abstract
Bundling individual quality measures into composite indicators is now a widespread practice, but is prone to multiple problems. They include lack of transparency in reporting, use of flawed methodological approaches, weaknesses in how measures are standardised and combined, and failure to describe statistical uncertainty of scores or rankings. Often, these problems make it difficult or impossible to understand what a composite indicator actually measures. Consequently, comparing organisations on what appears to be the same basket of quality indicators is rarely straightforward. Efforts to improve the transparency, scientific grounding and practical usefulness of composite indicators are much needed.
Keywords
Humans, Reproducibility of Results, Health Services Research, Quality of Health Care, Quality Assurance, Health Care, Quality Indicators, Health Care
Sponsorship
Wellcome Trust
Cancer Research UK
Identifiers
External DOI: https://doi.org/10.1136/bmjqs-2018-007798
This record's URL: https://www.repository.cam.ac.uk/handle/1810/279616
Rights
Attribution 4.0 International (CC BY 4.0)
Licence URL: https://creativecommons.org/licenses/by/4.0/