Mortality analysed by propensity matching
N. T. Longford
Abstract
Mortality, a key outcome variable in many population studies and
studies of healthcare and its interventions, is commonly analysed
by regression of the survival status on a set of relevant background
variables.
We describe an alternative based on the potential outcomes framework,
in which we ask how a particular group of subjects, or a population,
whose outcomes were realised in one condition, would have fared
had they been treated or cared for in different circumstances.
The method is applied to neonatal mortality in the operational delivery
networks in England and Wales.
The performance of a network is assessed by the difference
of the mortality rates of the network and of a matched set of babies
drawn from the entire domain of the study.
The outlier status of a network is established by a decision-theoretical
approach.
Submitted.
April 2021.