MaskedPrior.create_likelihood_variable#
- MaskedPrior.create_likelihood_variable(name, *, mu, observed)[source]#
Create an observed variable over the active subset and expand to full dims.
- Parameters:
- name
str Base name for the created variables.
- mu
pt.TensorLike Mean/location parameter broadcastable to the masked shape.
- observed
pt.TensorLike Observations broadcastable to the masked shape.
- name
- Returns:
pt.TensorVariableDeterministic variable over the full dims with observed RV on active entries.