In this section
@article{Longford:2020:10.1111/rssa.12529,
author = {Longford, N},
doi = {10.1111/rssa.12529},
journal = {Journal of the Royal Statistical Society Series A: Statistics in Society},
pages = {1363--1385},
title = {Performance assessment as an application of causal inference},
url = {http://dx.doi.org/10.1111/rssa.12529},
volume = {183},
year = {2020}
}
TY - JOUR
AB - Institutions in health care, education and other public services are under constantpressure to perform to high standards and with efficiency. Assessment of theirperformance is often problematic because it either ignoresimportant backgroundvariables of their patients, students or clients (the case-mix), or adjusts for themin a way that is not equitable or transparent. We apply a methodof indirectstandardisationmotivated by the potential outcomes framework, in which weconsider the hypothetical scenario of an institution’s caseload being dispersed fortreatment throughout the domain of assessment (the country’s institutions). Thetarget of estimation is the difference of the means of the outcomes in the realisedand hypothetical settings. The method is applied to estimating the prevalenceof bronchopulmonary dysplasia (BPD) in extremely preterm-born infants in theneonatal units and their networks in Great Britain in 2017. The prevalence ofBPD is an audit measure in the UK National Neonatal Audit Programme.
AU - Longford,N
DO - 10.1111/rssa.12529
EP - 1385
PY - 2020///
SN - 0964-1998
SP - 1363
TI - Performance assessment as an application of causal inference
T2 - Journal of the Royal Statistical Society Series A: Statistics in Society
UR - http://dx.doi.org/10.1111/rssa.12529
UR - http://hdl.handle.net/10044/1/74310
VL - 183
ER -
Neonatal Medicine Research Group and Neonatal Data Analysis Unit Manager
(All research related queries)
Room G 4.3
Chelsea and Westminster Hospital
ndau@imperial.ac.uk
+44 (0)20 3315 5841
Research Communications Lead
(Communications related queries only)
dsakyi@imperial.ac.uk
