I’ve just released Version 1.2 of the toolbox ‘Bayesian analysis toolbox for delay discounting.’ The main feature of this release was the addition of new models. For example, you can now estimate discount rates (ignoring the magnitude effect). So you can obtain estimates of the discount rate k, which is very useful if your primary concern is just to estimate discount rates for participants. Also, I have added non-hierarchical versions of the models which estimate a) discount rates, b) magnitude effects. These are useful when you know a priori that your participants do not come from a homogeneous group.

Along with the new model to estimate discount rates, we have a nice visualisation (left) of the posterior distribution of log(k), and participant response data and their discount function (right). Light grey lines show 100 samples from the posterior distribution of the log(k) parameter.


Go get the paper and code here:

Vincent, B., T. (in press) Hierarchical Bayesian estimation and hypothesis testing for delay discounting tasks, Behavior Research Methods. doi:10.3758/s13428-015-0672-2 [pdf | Matlab code on GitHub]


Go to the Bayesian analysis toolbox for delay discounting data project page for more.

Leave a comment

Leave a Reply