Identifying and quantifying variation between healthcare organisations and geographical regions: using mixed-effects models. Issue 12 (18th September 2019)

• Record Type: Journal Article
• Authors: Abel, Gary; Elliott, Marc N
• Is Part Of: BMJ quality & safety. Volume 28:Issue 12(2019)
• Page Start: 1032
• Page End: 1038
• Publication Date: 2019-09-18
• Subjects: healthcare quality improvement -- performance measures -- quality measurement -- statistics; Medical care -- Quality control -- Periodicals; Health facilities -- Risk management -- Periodicals; Medical errors -- Prevention -- Periodicals; 362.106805
• DOI: 10.1136/bmjqs-2018-009165
• Languages: English
• ISSNs: 2044-5415

Abstract

Abstract : When the degree of variation between healthcare organisations or geographical regions is quantified, there is often a failure to account for the role of chance, which can lead to an overestimation of the true variation. Mixed-effects models account for the role of chance and estimate the true/underlying variation between organisations or regions. In this paper, we explore how a random intercept model can be applied to rate or proportion indicators and how to interpret the estimated variance parameter.