Model Identifiability
Guan‐Hua Huang · Wiley StatsRef: Statistics Reference Online · 2016
Abstract A model is identifiable if there is a one‐to‐one correspondence between the probability distribution of the data and the values of model parameters. When applying a nonidentifiable model, different people may draw different conclusions from the same model of the observed data. Before one can meaningfully discuss the estimation of a model, model identifiability must be verified.