Prediction tests in limited dependent variable models
From MaRDI portal
(Redirected from Publication:1104020)
This paper discusses the problem of assessing the predictive power of a model in the class of limited dependent variable models. The use of dummy variables in this context in standard regression models has been discussed in \textit{D. S. Salkever}, J. Econ. 4, 393-397 (1976; Zbl 0348.62032), however problems emerge if such an approach is taken when the dummy appears in a limit of an integral that has to be evaluated. The paper proposes tests of predictive power which circumvent these problems.
Recommendations
Cites work
- Exogeneity
- scientific article; zbMATH DE number 3837235 (Why is no real title available?)
- scientific article; zbMATH DE number 3271181 (Why is no real title available?)
- On the existence of maximum likelihood estimates in logistic regression models
- On the formulation of empirical models in dynamic econometrics
- Specification Tests for the Multinomial Logit Model
- Tests of Equality Between Sets of Coefficients in Two Linear Regressions
- The structure of simultaneous equations estimators
- The structure of simultaneous equations estimators. A comment
- The use of dummy variables to compute predictions, prediction errors, and confidence intervals
Cited in
(5)- scientific article; zbMATH DE number 3860264 (Why is no real title available?)
- Efficient specification tests for limited dependent variable models
- scientific article; zbMATH DE number 4062441 (Why is no real title available?)
- scientific article; zbMATH DE number 4104666 (Why is no real title available?)
- Missing measurements in limited dependent variable models
This page was built for publication: Prediction tests in limited dependent variable models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1104020)