I am modelling left censored data. Following Stan’s manual, I have integrated out censored values in the model block. However, testing the code with 1 chain produced the following error:
Chain 1: Rejecting initial value: Chain 1: Log probability evaluates to log(0), i.e. negative infinity. Chain 1: Stan can't start sampling from this initial value.
but sampling still did complete.
My question is, can the result be trusted with this error?