Neurophysiology of Active Perception

====== Psychometrics ====== My PhD project, supervised by Paul De Boeck, was in psychometrics. My thesis was about probabilistic modelling of behavioral responses that come in the form of a subjects-by-stimuli/items matrix. My main contribution to psychometrics was the development of a new class of probabilistic models, called latent response models (LRMs). LRMs are very useful for the modelling of cognitive processes which, in a probabilistic modelling framework, are latent random variables that are mapped on an observed random variable (accuracy, response time) according to some rule (e.g., conjunctive, disjunctive, winner-take-all) that follows from the postulated cognitive process. Moreover, LRMs are analytically tractable because their parameters can be estimated using the expectation-maximization and the data-augmentation algorithm, which both make use of the missing data structure of LRMs. I supervised four PhD projects in psychometrics, all of which involved probabilistic modelling of cognitive processes: * Javier Revuelta (University of Madrid) A Psychometric Model for Multiple Choice Items. May 2000 (co-supervisor together with Vicente Ponsoda). * Francis Tuerlinckx (University of Leuven) Some Extensions and Applications of Item Response Theory Models and Diffusion Models. December 2000 (co-supervisor together with Paul De Boeck). * Tom Verguts (University of Leuven). Process Models of Rule Induction Tasks. March 2001 (co-supervisor together with Paul De Boeck). * Gunter Maris (University of Nijmegen). Statistical Contributions to Psychological Modelling. December 2001.