Least Squares Regression with Integrated or Dynamic Regressors under Weak Error Assumptions
- 11 February 1987
- journal article
- research article
- Published by Cambridge University Press (CUP) in Econometric Theory
- Vol. 3 (1) , 98-116
- https://doi.org/10.1017/s026646660000414x
Abstract
This paper establishes consistency of least squares estimators in (i) a multiple regression model with integrated regressors and explosive, non-mixing errors, and (ii) a dynamic linear regression model with regressors and errors that may have infinite variances. In the former context, the asymptotic distribution of the least squares estimator also is obtained, in certain cases.Keywords
This publication has 33 references indexed in Scilit:
- Understanding spurious regressions in econometricsPublished by Elsevier ,2002
- Stability Comparison of EstimatorsEconometrica, 1986
- The Exact Distribution of the Wald StatisticEconometrica, 1986
- A nearly independent, but non-strong mixing, triangular arrayJournal of Applied Probability, 1985
- A Unified Theory of Consistent Estimation for Parametric ModelsEconometric Theory, 1985
- A Zero-One Result for the Least Squares EstimatorEconometric Theory, 1985
- A Functional Central Limit Theorem for Weakly Dependent Sequences of Random VariablesThe Annals of Probability, 1984
- Conditions for linear processes to be strong-mixingProbability Theory and Related Fields, 1981
- Some Large-Sample Tests for Nonnormality in the Linear Regression ModelJournal of the American Statistical Association, 1980
- On Consistency in Time Series AnalysisThe Annals of Statistics, 1978