|
Abstract:
|
In a critique on the foundations of a large and diverse literature in economics, we obtain the likelihood function of simultaneous equation models for discrete data as the invariant distribution of a suitably defined Markov chain. Our formulation provides a well-defined reduced form of the model and dispenses with controversial recursivity requirements and the need to augment the data generating process with ad hoc indeterminacy rules. We demonstrate that the likelihood is unique, proper, coherent, complete, and theoretically grounded in conditional distribution modeling -- a framework that has yet to be popularized in economics. We briefly examine extensions, relevant links, and computational issues, and present an application to a lender-of-last-resort program in banking during the Great Depression.
|
