The Theory of Reduction
Twelve stages of reduction are delineated from the actions of agents in an economy to an econometric model. The actual measurement process induces the DGP, followed by data transformations and aggregation; formulating parameters of interest; and partitioning the data. Marginalization, sequential factorization, the mapping to I(0), and conditional factorization can involve considerable loss of information if inappropriately implemented. Constancy, lag truncation, and functional form are discussed, leading to the derived model. The main concepts of econometrics arise as measures of ‘no loss of information’ about parameters of interest during a reduction. The reduction sequence also entails a taxonomy of information sets for model evaluation. These clarify the relation of model‐selection criteria to the null hypotheses of test statistics. Implicit model design is criticized in favour of an explicit approach.
Oxford Scholarship Online requires a subscription or purchase to access the full text of books within the service. Public users can however freely search the site and view the abstracts and keywords for each book and chapter.
If you think you should have access to this title, please contact your librarian.