Skip to main content

Detail

Sonja Zehetmayer
Sonja Zehetmayer

Center for Medical Statistics, Informatics and Intelligent Systems (Institute of Medical Statistics)
Position: Associate Professor

ORCID: 0000-0001-6863-7997
T +43 1 40400 74850
sonja.zehetmayer@meduniwien.ac.at

Further Information

Keywords

Biostatistics; Epidemiology; Genetics; Models, Statistical

Research interests

My research interests include statistical application and multiple testing in genetics in the context of a large number of hypothesis tests (e.g., microarray analysis, RNA-seq, etc.). Here I focus on the optimal study design of experiments with sequential methods while controlling the error rate (False Discovery Rate and Family-Wise Error Rate). Another research focus lies on the development of a new statistical test for the global null hypothesis and testing subgroups with the closed testing principle.

Techniques, methods & infrastructure

An R-package for testing the global null hypothesis with the omnibus test is available (https://github.com/ThomasTaus/omnibus/blob/master/DESCRIPTION). An extended R-package including the test for subgroups is in preparation.

Grants

  • Repeated Significance Tests controlling the False Discovery Rate (2009)
    Source of Funding: FWF (Austrian Science Fund), Hertha Firnberg grant
    Principal Investigator

Selected publications

  1. Futschik A, Taus T, Zehetmayer S. An omibus test for the global null hypothesis. Stat.Methods in Medical Research. Published online 2018. To Appear.
  2. Zehetmayer S, Graf AC, Posch M. Sample size reassessment for a two-stage design controlling the False Discovery Rate. (2015) Statistical Applications in Genetics and Molecular Biology. 14(5):429-42.
  3. Zehetmayer S, Posch M. FDR control in two-stage designs. (2012) BMC Bioinformatics. 13:81.
  4. Zehetmayer S, Posch M. (2010). Post-hoc power estimation in large scale multiple testing problems. Bioinformatics. 26, 1050-1056.
  5. Zehetmayer S, Bauer P, Posch M. (2005). Two-stage designs for experiments with a large number of hypotheses. Bioinformatics. 21, 3771,