6 entries
probability distributions experimental design
A distributional estimate can be mathematically tidy while the design that generated its observations left whole groups outside it. Distribution parameters and experimental allocation are two halves of the same claim.
historical institutions empires
States produce records where they can administer, not everywhere they claim. Institutions and empires make the missing edge visible: a ledger of offices is not a map of practical control.
archaeological sites historical documents
The absence of a find can mean nonexistence, nondeposition, nonrecovery, destruction or misclassification. Site records and document history built separate checks because a blank field cannot tell you which one happened.
ancient civilizations archaeological sites
The most visible site can carry the best measurements and the worst representativeness. Civilizational collapse studies and site records both require the writer to say what was sampled, what survived and what remains unopened.
A practice can continue after its stated mechanism has failed every available check. Folk belief and oral transmission make persistence a measurement in its own right, not a proof of what kept the practice alive.
textual criticism experimental design
Finance corrects for survivorship. Clinical trials count every loss. Textual critics rebuild the missing ones and report their page dimensions.