Weighing evidence steampunk style with the Meta-Analyser

Meta-analysis is the science of weighing the evidence available from different sources in order to arrive at the most sensible and informed conclusion to a given question. The technique has a long history in medical research, where it is routinely used to aggregate results from independent clinical trials testing competing therapies (for example which is better: treatment A or B? And by how much?). Whilst each study may be too small or imprecise to definitively answer the clinical question on its own, the overall estimate delivered by a meta-analysis can often do so, thus negating the need to perform further costly research. It is therefore a useful tool in a statistician’s armoury and a major focus of our research at the MRC Biostatistics Unit (BSU).

CSF 1Cambridge Science Festival is an event for Cambridge academics working across the scientific spectrum to promote and explain their current research to the general public. In 2014, scientists at the BSU came up with a mechanical device, named the `Meta-Analyser' to explain the concepts of weighing evidence and of biased evidence to a young audience at the festival. By equating the process of determining the centre of mass of a physical system, to conducting a meta-analysis of clinical trials, we were able to explain important and complex statistical methods without using precise definitions or statistical formulae.

The exciting invention, created by Jack Bowden and Chris Jackson at BSU, was introduced within the context of a steampunk inspired mystery involving Ada Lovelace and Sherlock Holmes - see picture of the Meta-Analyser in action at Cambridge Science Festival.

Following on from the science festival, we have developed an interactive web-application (called the Meta-Analyser) to bring these ideas to a wider audience of students and researchers. The app extends the basic idea introduced at the festival to enable extended modelling choices, such as random effects models and meta-regression. It can be found at: https://chjackson.shinyapps.io/MetaAnalyser/.

This work has also been written up and accepted in the American Statistician, to appear in 2016. In accordance with the journal’s policy, a copy of the first submitted version of the manuscript is available to download here: BowdenJackson2015_1stSub. The final corrected version will be available (and made open access) on the journal website shortly.

The MRC Biostatistics Unit will be at this year’s Cambridge Science Festival on Saturday 12th March at the Guildhall in Cambridge and also on Sunday 20th March at the Clinical School on the Addenbrooke’s Hospital site. Come along to find out more about the exciting research we are doing with activities for all ages on Genes and Lifestyle, Adaptive Randomisation and Biased Sampling.