Do We Need Higher-Order Probabilities and, If So, What Do They Mean?
The apparent failure of individual probabilistic expressions to distinguish uncertainty about truths from uncertainty about probabilistic assessments have prompted researchers to seek formalisms where the two types of uncertainties are given notational distinction. This paper demonstrates that the desired distinction is already a built-in feature of classical probabilistic models, thus, specialized notations are unnecessary.
PDF Link: /papers/87/p47-pearl.pdf
AUTHOR = "Judea Pearl
TITLE = "Do We Need Higher-Order Probabilities and, If So, What Do They Mean?",
BOOKTITLE = "Proceedings of the Third Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-87)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "1987",
PAGES = "47--60"