Christopher Jackson

Evidence synthesis and evaluation of health policies.

Health policies, such as the introduction of new treatments, are commonly evaluated using decision-analytic models. These models combine all relevant evidence from multiple sources, commonly extrapolate it to the long term, and involve a lot of uncertain assumptions. Chris's work involves statistical methods to ensure that the decisions based on these models accurately reflect the available evidence. The extent and sources of uncertainty are also quantified to ensure that priorities for future research are set appropriately.  A Bayesian framework is typically used, which allows direct data, indirect data and expert belief to be combined. Chris has been appointed to the editorial board of the journal Medical Decision Making for the 2018-2020 period.  

Multi-state models for longitudinal data

Multi-state and time-to-event models in health care and disease progression. Chris maintain the msm R package for continuous-time Markov and hidden Markov modelling.  

Statistical computing

Developing and maintaining several R packages, including msm, flexsurv for survival analysis, denstrip for illustrating distributions, ecoreg for ecological inference. Contributing to the OpenBUGS and BRugs software for Bayesian analysis.  

Recent presentations

• Slides from the ENAR Biometrics Webinar on multi-state modelling, October 2017

 

Google Scholar profile