Skip to main content


Susanne Urach
MMag Susanne Urach, BSc

Center for Medical Statistics, Informatics and Intelligent Systems (Institute of Medical Statistics)
Position: PHD Student

T +43 1 40400 74840

Further Information


Biostatistics; Rare Diseases

Research group(s)

Research interests

In general my area of expertise consists of biostatistics and the statistical analysis of clinical trials. Specifically my fields of interest include statistical methods to adjust for multiple testing and adaptive trial designs, whereby certain aspects of the design (e.g. trial duration and sample size) can be adapted in interim analyses, taking account of the data aggregated so far.

Techniques, methods & infrastructure

As patients are not all enrolled in a trial at the same time, but continuously, interim analyses can be performed after the outcome of a certain number of patients was measured. Adaptive trials allow one to make use of accumulating data to either stop the trial early after an interim analysis or to continue and adapt the trial. Special analysis methods have to be applied to maintain the validity of the adaptive trial. The flexibility can increase the robustness of the trial with respect to misspecifications of planning assumptions.

If several hypotheses are tested using the same significance level alpha, the probability of finding at least one significant result even when there is no effect is in general higher than alpha. When trying to test several hypotheses in a clinical trial in a confirmatory way, one has to control the probability to wrongly reject at least one true null hypothesis (multiple type I error rate). Different adjustment methods for multiple hypothesis tests making different degrees of assumptions exist to achieve multiple type I error rate control.

The operating characteristics of adaptive designs and multiple testing procedures are evaluated using the R programming language.

Selected publications

  1. Urach, S. & Posch, M., 2016. Multi-arm group sequential designs with a simultaneous stopping rule. Statistics in Medicine, 35(30), pp.5536-5550. Available at: