It looks like there’s a typo in the log-likelihood formula. In B4, there is a summation only over the final term.
Also why use Metropolis? I’m pretty sure NUTS should be able to fit this model.
1 Like
It looks like there’s a typo in the log-likelihood formula. In B4, there is a summation only over the final term.
Also why use Metropolis? I’m pretty sure NUTS should be able to fit this model.