How much data are needed to obtain useful parameter estimations from a computational model? The standard approach to address this question is to carry out a goodness-of-recovery study. Here, the correlation between individual-subject true and estimated parameter values determines when a sample size is large enough. However, depending on one’s research question, this approach may be suboptimal, potentially leading to too small (underpowered) or too large (overcostly) sample sizes. Therefore, we formulate a generalized concept of statistical power, and use this to propose a novel approach toward determining how much data is needed to obtain useful parameter estimates from a computational model. This novel approach is implemented in a python-based toolbox (COMPASS). All materials to use COMPASS are freely available at  https://github.com/CogComNeuroSci/COMPASS. In the presentation I will first discuss some theoretical background for the toolbox, then I will provide some concrete applications and go through all the steps that are needed to perform your own power computations.

Pieter VerbekePost-doc researcherGhent University

Pieter Verbeke – COMputational Power Analyses using SimulationS: A tutorial on the COMPASS toolbox