The SIG is led by Professor Amanda Mocroft and Dr Alessandro Cozzi-Lepri of the HIV Epidemiology and Biostatistics Group of University College London, London UK
The SIG includes senior and junior statisticians as well as PhD students in PERSIMUNE affiliated to PER-SIMUNE University partners, in addition to those with an interest in methodology, statistical analysis or interpretation of data. The main aim/task of the SIG is to collaborate with clinical and scientific staff in PERSIMUNE in the design, implementation, analysis and reporting of medical research.
• To provide methodological strength and statistical rigour to interdisciplinary (collaborative) cli-nical research programmes across PERSIMUNE.
• To be a Centre and natural home for all career statisticians working in PERSIMUNE: to provide them with a professional peer group; access to broader and higher-level statistical expertise; support for professional development; and opportunities to develop cross-collaborations.
• To provide statistical training and support to existing and proposed projects, based on excel-lence in statistical methodology at all stages of research, from study design through data collection, analysis and publication. In this way, to facilitate the winning of major clinical research grants and the placing of publications in the most highly esteemed academic journals.
• To provide an open and welcoming forum for anyone with an interest in statistics to discuss both individual projects or more general methodological issues
Methodological interests and strengths
The SIG have a wide range of methodological interests and strengths including:
The design and analysis of epidemiological and other observational studies;
The design and analysis of nested case control studies;
The design and analysis of randomised trials and other clinical experiments (including the evaluation of complex interventions);
Survival and Poisson regression analysis including risk modelling and development and validati-on of prognostic scores
Complex statistical modelling, applications to high-dimensional biomarker data and clustered or correlated outcomes arising from measurements repeated over time (including repeated events or interventions);
Modern statistical approaches to causal inference;
For more information please contact
Amanda Mocroft (email@example.com)
Alessandro Cozzi Lepri (firstname.lastname@example.org)
PM secretariat (email@example.com)