On an Identity Derived from Unbiasedness in Linear Models
C. E. McCulloch, S. R. Searle · The American Statistician · 1995
Difficulties associated with deriving AX = X as a necessary condition from Ay + c being an unbiased estimator of X{J are discussed in terms of the linear model y"' (X{J, V).We demonstrate two instances in which AX = X and c = 0 are not necessary conditions but then argue that these can be ignored in practice.Excluding these possibilities leads to AX = X and c = 0 being necessary.