What is meant by 'P(R|Yobs)'?
Missing at Random (MAR) is a central concept in incomplete data methods, and often it is stated as P(R3mu| Y_obs, Y_mis) = P(R3mu| Y_obs). This notation has been used in the literature for more than three decades and has become the de facto standard. In some cases, the notation has been misinterpreted to be a statement about conditional independence. While previous work has sought to clarify the required definitions, a clear explanation of how to interpret the standard notation is lacking. Specifically, it has not been explained clearly why neither P(R3mu| Y_obs, Y_mis) nor P(R3mu| Y_obs) are to be interpreted as probability distributions in this statement, and a definition of the function P(R3mu| Y_obs) for non-MAR mechanisms is difficult to locate in the literature. The latter is needed if the standard statement is to provide a useable testable condition. The aim of this paper is to fill these gaps.
READ FULL TEXT