Biostatistics and Medical Biometry

Many studies on the same research question often provide many different results. Meta-analysis deals with the synthesis of these into a statistically more powerful aggregate. We are currently working on the development and application of methods for the meta-analysis of diagnostic test accuracy studies. We aim to develop methods that summarise all the information available in the primary studies in a fair and unbiased way.

In many areas of medical research, the time until an event occurs (such as death or remission) is the primary endpoint. A key difference from other data situations is that event times may not be fully observed during the course of the study. Survival analysis deals with modeling such "censored" data that cannot be properly analyzed using conventional statistical methods. We are currently working on developing new methods for survival analysis that are suitable for complex study designs and provide intuitive results for practical application.