SBC
SBC copied to clipboard
hyunjimoon
Bootstrapped synthetic likelihood could prevent the repeated N times of fitting; resampling from one set of recovered parameters with some estimated variance could be used to approximate SBC_vanila's computation. The...
## summary A tool that could point to the next region of sample space that affects Bayes factor (BF) the most. Decision/inference based on BF workflow follows [this](https://arxiv.org/abs/2103.08744) paper. ##...
## summary SBC does not require real-world data in principle. However, it could be used to trim some extreme and unrealistic simulated datasets. ## expected effect - prevent the need...
update the hyperparameter value iterative with `d_lp/d_hp` 1. start with a rough estimate of hyperparameter value 2. get `d_lp/d_hp` one stan fit via `grad_log_prob` 3. update hp value and plug...
Package could provide the scope of prior parameter based on SBC result as follows:  experiment results on different prior settings  Figure 10: SBC histogram with different prior parameters...