|
Abstract:
|
This work is motivated from a real dataset collected from an eye-tracking study of attention in learning. Stochastic continuous-time models with interpretable parameters have been proposed to analyse each subject data. Tor each trial, the observed data consists of the sequence of stimulus features that the subject fixates on, together with the duration of each fixation. However, the parameter estimation for stochastic differential equation systems is quite challenging. We explored the possibility of using the Approximate Bayesian Computation framework to solve this problem.
|
