实证研究的目的和重点可以用下面的话来说明:
The ultimate goal of econometrics is to learn about causal relationships from micro
data capturing non-experimental economic behavior. This is hard in principle because
social sciences differ from, e.g., medicine where (double-blind) randomized
experiments are the way to learn. There are often elusive unobservables affecting
the outcome; hence, the need for sample selection (treatment assignment) control.
Economic processes often lead to simultaneity so that we need exogenous
(experiment-like) variation. Econometrics differs from statistics in defining the
identification problem: structural and reduced-form equations.
|