scientific article; zbMATH DE number 3938401
For a number of years criteria of quality of econometric models have been under discussion. The author expresses the opinion that to judge the goodness of a model the concept of the ideal model is to be introduced. The goodness of a model can be defined only in terms of the ideal model, in accordance with the rule that better is an enemy of good. The following features are included into the concept of the ideal model: a)feasibility, i.e. close to one probability that the values of the explained variables will fall within the 3 sigma interval around the values from the model, b) independence of explanatory variables, c) coincidence of the estimates of the parameters of the model, i.e. the identity of signs of the regression coefficients and those of the corresponding correlation coefficients, d) invariance of the estimates of parameters with respect to exclusion from or incorporation into the model of a new explanatory variable.
- scientific article; zbMATH DE number 3974145
- scientific article; zbMATH DE number 3886946
- scientific article; zbMATH DE number 3856267
- On the statistical identification of DSGE models
- Identification and Inference for Econometric Models
- Identification and Inference for Econometric Models
- Identifiability of a simultaneous equations model of economy: a structural view
- Parameter identification of a class of economical models
- Inference for identifiable parameters in partially identified econometric models
- Some peculiarities of identification in the presence of model errors
- Econometric modeling using ``Goodness of fit of behavior
- The asymptotic model quality assessment for instrumental variable identification revisited
- Economic modelling and its quality components
- scientific article; zbMATH DE number 3967768 (Why is no real title available?)
- scientific article; zbMATH DE number 3974145 (Why is no real title available?)
- scientific article; zbMATH DE number 1538093 (Why is no real title available?)
- Assessing the quality of identified models through the asymptotic theory -- when is the result reliable?
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3709750)