 |
 |
DCM experts, I know that there is a way (spm_dcm_post_hoc) to use a greedy search to do Bayesian model selection when there are many free parameters in a model space, but I was wondering if there are any similar tricks to use if the end goal is to do Bayesian model averaging instead? I'm guessing that the answer is no, since to do model averaging we actually have to estimate the model parameters for all the models we want to average, while the greedy search for more than 16 free parameters seems conceptually similar to a backwards stepwise regression, iteratively trying removal of different parameters from the overall model to quickly find the best fit, without necessarily estimating every possible model. -- Mike Angstadt Research Computer Specialist / PANLab Lab Manager Department of Psychiatry / University of Michigan (734) 936-8229 ********************************************************** Electronic Mail is not secure, may not be read every day, and should not be used for urgent or sensitive issues