Statistical Inference Methods for Neuroeconomics

• Applicant: Professor Dr. Thorsten Dickhaus
• Subject Area: Statistics and Econometrics
• Term: from 2013 to 2018
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 239049500

• Final Report Year: 2019

Final Report Abstract

The project deals with statistical methods for analyzing neuroeconomics data. In particular, the project considers multiple test problems with a family of hierarchically structured (null) hypotheses in the fMRI context. The project has delivered a new data analysis method (multiple test) which is an extension of the approach by Schildknecht et al. (2016). The extension consists of considering more than two layers of hierarchy and to account for the thereby increased multiplicity of the testing problem in a closed testing based manner which avoids loss in statistical power. Thus, the project results contribute to extracting more information out of fMRI data than previous approaches.

Publications

• More Specific Signal Detection in Functional Magnetic Resonance Imaging by False Discovery Rate Control for Hierarchically Structured Systems of Hypotheses. PLoS One 11(2): Article e0149016
  Schildknecht, Konstantin; Tabelow, Karsten & Dickhaus, Thorsten