Centre for Statistical Methodology

The Centre for Statistical Methodology aims to gather statistical and methodological expertise across the School in order to strengthen our research capacity in epidemiology and public health.

Welcome to the LSHTM Centre for Statistical Methodology

The LSHTM Centre for Statistical Methodology aims to gather statistical and methodological expertise across the School in order to strengthen our research capacity in epidemiology and public health, and exploit the richness and interdisciplinarity of the work carried out within the School. This is in line with the School’s strategic plans for sustaining areas of established expertise in which we have an international reputation.

Read more

Next CSM Seminar

The Centre hosts regular seminars across the different themes. The next seminar is:

Centre for Statistical Methodology Seminar Friday 14 December 2018, 12:45-2:00pm LG9, Keppel Street Design and analysis of trials where the outcome is a rate of change, with an introduction to a new Stata package for sample size calculation Chris Frost and Amy Mullick (LSHTM) Abstract: A number of different approaches can be used to analyse clinical trials with a continuous outcome measured at baseline, and at several follow-up times. We first describe the general utility of linear mixed models in this setting, with a particular emphasis on trials where the aim of treatment is to slow disease progression as measured by a rate of change in the outcome. We go on to show how the statistical efficiency of, and hence required sample sizes for, such trials depends on factors such as the length of the trial and the frequency of follow-up, and describe how analysis of existing longitudinal observational data can be used to inform trial design decisions. We use data from a longitudinal study of people with Huntington’s disease to illustrate the methodology. We also introduce a new user-friendly Stata package for sample size calculation, appropriate for planning a two-arm parallel trial of treatment that is expected to slow disease progression by a constant amount over multiple follow-up visits. The package fits a linear mixed model to a user-supplied longitudinal dataset, extracting relevant parameters to estimate mean rates of change and components of between- and within-person variability. These estimates, together with other user inputs, are then used to calculate the required sample size for a proposed trial. Users specify the visit schedule, expected loss to follow up rates, Type I and Type II error rates, and the target effectiveness of the treatment.

Read more

Recent seminar slides & audio

Slides and audio recordings of many of our previous seminars are available. Our most recent seminars have been:

Missing Data Theme
Uncertainty and missing data in dietary intake and activity data.
Graham Horgan (Rowett Institute, University of Aberdeen)
Slides available soon

Clinical Trials Theme
Lessons learned from implementing a stratified medicine master protocol: The National Lung Matrix Trial
Prof Lucinda Billingham (University of Birmingham)
Slides available soon

Read more

Sequential Trials Symposium

The Centre for Statistical Methodology and the Tropical Epidemiology Group of the London School of Hygiene & Tropical Medicine held a half day symposium on sequential trials on the afternoon of 26 September 2018.

Read more

"Statistical Methods for Big Data” Symposium

The Centre for Statistical Methodology held a half-day symposium on Statistical Methods for Big Data on 7 July 2017. The symposium aimed to discuss features of Big Data and the challenges that they pose for statistical methods and future directions of research. Speakers from different methodological perspectives presented examples across a wide spectrum of applications.

Read more