Research Seminar
Hierarchical diffusion models for choice response timeJoachim VandekerckhoveKU Leuven | |
| Abstract: | The Wiener process is a popular and parsimonious model for choice reaction time data. In this talk, we present a hierarchical extension of the model. In doing so, we explicitly consider the Wiener process as a measurement model in the psychometric sense and exploit the various modeling opportunities this provides. This approach - an instance of "cognitive psychometrics" - allows us to apply diffusion models in a variety of new paradigms. In particular, in the hierarchical framework we can disentangle different sources of parameter variability (e.g., item variance, population variance, trial variance; a multilevel diffusion model), and attempt to explain parts of these variabilities through the inclusion of covariates (an explanatory diffusion model). Additionally, hierarchical diffusion models can be applied to data sets with many participants but relatively few observations per participant, something which has been problematic with previous implementations. We will demonstrate the relative ease with which these analyses can be performed and show results from an empirical data set. |
| Date: | Tue Apr 15, 12:15 pm - 1:15 pm |
| Place: | room 00.60 (Department of Psychology, Tiensestraat 102, 3000 Leuven) |