RE: Bayesian Process module
RE: Bayesian Process module.
It doesn't have Missing value handling (e.g., using Full Information Maximum Likelihood, which is what I would really like).
Is this an oversight, or coming, or just incompatible with Bayesian, and so will never be implemented?
Comments
Hmm. But maximum likelihood is not Bayesian. I will ask the relevant team member about missing data in the Bayesian process module.
EJ
The Classic Process Analysis has two types of missing value handling: Listwise deletion and Full Information Maximum Likelihood (FIML) estimation. The Bayesian Process Analysis does not have this distinction due to its reliance on blavaan. It automatically handles missing values using the full information likelihood similar to FIML in the classic module. See https://stackoverflow.com/questions/69336008/how-to-deal-with-missing-data-using-blavaan which was answered by the author of blavaan. I hope this helps!
Best,
Malte