Back to top

Dr Jennifer Rogers

Director of Statistical Consultancy Services

OxCSML Group

+44 (0)1865 272860 (Department)
+44 (0)1865 281279 (Direct)

Biographical Sketch

I completed my BSc in Mathematics and Statistics in 2006 at Lancaster University. I then remained at Lancaster University for my MSc in Statistics, which I received in 2007. Following this, I moved to the University of Warwick, Department of Statistics, where I completed my PhD in Statistics in March 2011, under the supervision of Prof. Jane Hutton. My thesis is titled: ‘Statistical Models for Censored Point Processes with Cure Fractions’ and develops a new class of statistical models that jointly analyse pre-randomisation seizure rates and post-randomisation survival times in clinical trials for epilepsy. The application of my thesis was to assess the benefit of immediate versus deferred treatment in those patients with early epilepsy or single seizures.

I joined the London School of Hygiene and Tropical Medicine Department of Medical Statistics as a Research Fellow in May 2011 and was promoted to Lecturer in October 2013. At the LSHTM, my research mainly focussed on developing and implementing appropriate methodology for the analysis of repeat hospitalisations in patients with heart failure. I was awarded a three year NIHR Post-Doctoral Fellowship in September 2013 for a project titled: ‘Analysis of Recurrent Events in Clinical Trials’. I joined the Department of Statistics, University of Oxford in September 2015.

I currently sit on the Royal Statistical Society Council and am the Royal Statistical Society Honorary Officer for Meetings and Conferences. To see more information on appointments that I have previously held, as well as my public engagement and media activities, please take a look at my personal website.

Research Interests

  • Statistical methodology
  • Analysis of recurrent events
  • Survival analysis
  • Joint modelling
  • Latent variable modelling

My research is generally focused on statistical methodology, with applications of statistics to health care. My main area of research to date has been on the development and application of novel statistical methods for the analysis of large-scale clinical trials. My principal theoretical interests are survival analysis and the analysis of recurrent events with a particular interest in joint modelling strategies that combine the two. My current major medical collaborations are in cardiovascular disease and I am currently investigating methods for handling recurrent heart failure hospitalisations as an alternative to more standard composite endpoints in randomised clinical trials.

Standard analysis of composite endpoints (e.g. first heart failure hospitalisation and cardiovascular death) is limited to a time to first event analysis, which is suboptimal for a chronic disease such as heart failure, which is characterised by recurrent non-fatal events, as repeat events within individuals are subsequently ignored. An increase in heart failure hospitalisations, however, is associated with an increased risk of death and so censoring due to death is not independent of the recurrent event process. This dependent (informative) censoring must be incorporated into analyses.

The focus of my NIHR project is the development of new statistical models for the analysis of recurrent hospitalisations in heart failure in the presence of dependent censoring and has involved me investigating the relationship between recurrent heart failure hospitalisations and the competing risk of cardiovascular death. I have also been considering joint frailty models to model the dependency structure between recurrent hospitalisations in general and in the lead up to cardiovascular death. Joint frailty models assume that recurrent HF hospitalisations and time to death (or CV death) are conditionally independent given an individual-specific latent variable and allow distinct treatment effects to be estimated for each of the processes, whilst taking into account the association between the two.

Selected Publications

  • J.K. Rogers, A. Kielhorn, J.S. Borer I. Ford and S.J. Pocock. Effect of ivabradine on numbers needed to treat for the prevention of recurrent hospitalizations in heart failure patients. Current Medical Research & Opinion 2015; 31(10):1903-1909. doi: 10.1185/03007995.2015.1080155
  • J.K. Rogers, S.J. Pocock, J.J.V. McMurray, C.B. Granger, E.L. Michelson, J. Östergren, M.A. Pfeffer, S.D. Solomon, K. Swedberg and S. Yusuf. Analysing recurrent hospitalisations in heart failure: a review of statistical methodology, with application to CHARM-Preserved. European Journal of Heart Failure 2014; 16:33-40. doi: 10.1002/ejhf.29.
  • J.K. Rogers and J.L. Hutton. Comparing treatment policies in early epilepsy through the joint modelling of pre-randomisation event rates and multiple post-randomisation survival times. Journal of Applied Statistics 2013; 40(3):546-562. doi: 10.1080/02664763.2012.748720.
  • J.K. Rogers, J.L. Hutton, A.G. Marson, and D.W. Chadwick. Assessing the risk of subsequent tonic-clonic seizures in patients with a history of minor seizures. Journal of Neurology Neurosurgery and Psychiatry 2012; 83:803-809. doi: 10.1136/jnnp-2011-300917.