Statistical analysis plan for the proactive healthcare of older people in care homes (PEACH) study

The Proactive Healthcare for Older People living in Care Homes (PEACH) study aims to evaluate whether Quality Improvement Collaboratives can be an effective way to work with local health and social care stakeholders, including representatives of the care home sector, to implement Comprehensive Geriatric Assessment (CGA) in the care home setting. It will enlist the support of four Area Improvement Collaboratives from South Nottinghamshire, UK to make changes to enable CGA in care homes in their areas.

The primary outcome measure is health-related quality of life (HRQoL), measured using the EuroQoL 5-domain 5-level (EQ-5D-5L) index. A cluster-randomised (where care homes represent clusters) approach will be taken. Secondary outcome measures will be Health Service Resource by service category. These will be analysed using an interrupted time series approach.

The methodology is challenging and introduces the need to control for multiple sources of contamination, clustering, time effects including lag effect and measurement issues with the primary outcome variable, including the uncertain reliability of care home staff proxy responses.

This paper outlines the statistical analysis plan for the study, describing how these challenges have been addressed. It acts as reference point for further publications from the PEACH study.