REGRESSIONS WITH TWO SLOWLY VARYING REGRESSORS 1 Regressions with Two Slowly Varying Regressors: Hidden Discontinuities in Asymptotic Behavior
نویسندگان
چکیده
Asymptotic behavior of the OLS estimator for regressions with two slowly varying regressors is studied. It is shown that the asymptotic distribution may belong to one of four types depending on the relative rates of growth of the regressors. The paper expands and corrects recent results by P.C.B.Phillips (2007).
منابع مشابه
Regressions with Asymptotically Collinear Regressors
We investigate the asymptotic behavior of the OLS estimator for regressions with two slowly varying regressors. It is shown that the possibilities include a definite case, when the third-order regular variation is sufficient to determine the asymptotic distribution, and an indefinite case, when higher-order regular variation is required to find the distribution. In the definite case the asympto...
متن کاملNonlinear econometric models with cointegrated and deterministically trending regressors
This paper develops an asymptotic theory for a general class of nonlinear nonstationary regressions, extending earlier work by Phillips and Hansen (1990) on linear cointegrating regressions.The model considered accommodates a linear time trend and stationary regressors, as well as multiple I(1) regressors. We establish consistency and derive the limit distribution of the nonlinear least squares...
متن کاملThe Effect of Linear Time Trends on Cointegration Testing in Single Equations
This paper surveys the asymptotic distributions of three widely used single equation cointegration tests. Particular attention is paid to the case where the regressors are integrated with drift, i.e. at least one of the regressors follows a linear time trend. Even if the regressions are not detrended, the asymptotic critical values are affected by the presence of linear trends in the regressors...
متن کاملOn Asymptotic Normality When the Number of Regressors Increases and the Minimum Eigenvalue of X 0 X=n Decreases 1
Conditions under which a regression estimate based on p regressors is asymptotically normally distributed when the minimum eigenvalue of X 0X=n decreases with p are obtained. The results are relevant to the regressions on truncated series expansions that arise in neural networks, demand analysis, and asset pricing applications. 0
متن کاملBias Transmission and Variance Reduction in Two-Stage Estimation
In this paper, we study the transmission of an asymptotic bias in two-stage regressions with non-iid errors and random regressors in which the possible endogeneity of some explanatory variables is treated via first-stage predictive equations. In particular, we characterise the transmission of an asymptotic bias in the first-stage estimates to the secondstage estimates. As an example, we fully d...
متن کامل