Build a template class similar to MetaModel for generating posterior samples for Bayesian inference. This class should contain all the properties and some general functions that are expected for BayesInference. The current MCMC and rejection sampling implementations should become children of this class.
changed milestone to %2.0.0
added Inference Restructuring labels
marked this issue as related to #57 (closed)
We can estimate the IE and RE using the posterior samples obtained from the MCMC or the rejection sampling, depending on the user defined input, so that the criteria are not estimated using solely rejection sampling and then the posterior samples being obtained with another method. We can create a function for IE and RE, where we send the posterior samples.
We should be careful with the bootstrapping, since right now rejection sampling is used due to speed, since an IE and RE is estimatedfor each bootstrapping sample. This could be too expensive with MCMC, but for more complex cases rejection sampling might not be representative (dependning on the number of prior samples)
Done with !47 (merged)
closed