Comparing cointegrating regression estimators: Some additional Monte Carlo results
نویسنده
چکیده
This paper compares the finite sample performance of the canonical correlation regression estimator (CCR) and Stock and Watson's (A simple estimator of cointegration vectors in higher order integrated systems, Econometrica, 1993, 61(4), 783-820) dynamic ordinary least squares estimator (DOLS) using the models proposed by Inder (Journal of Econometrics, 1993, 57, 53-68). The CCR estimator shows smaller bias than the OLS and the fully modified. The DOLS estimator performs systematically better than the CCR estimator.
منابع مشابه
Asymptotic Properties of the Efficient Estimators for Cointegrating Regression Models with Serially Dependent Errors1
Abstract In this paper, we analytically investigate three efficient estimators for cointegrating regression models: Phillips and Hansen’s (1990) fully modified OLS estimator, Park’s (1992) canonical cointegrating regression estimator, and Saikkonen’s (1991) dynamic OLS estimator. We consider the case where the regression errors are moderately serially correlated and the AR coefficient in the re...
متن کاملAsymptotic Properties of the Efficient Estimators for Cointegrating Regression Models with Serially Dependent Errors
In this paper, we analytically investigate three efficient estimators for cointegrating regression models: Phillips and Hansen’s (1990) fully modified OLS estimator, Park’s (1992) canonical cointegrating regression estimator, and Saikkonen’s (1991) dynamic OLS estimator. First, by the Monte Carlo simulations, we demonstrate that these efficient methods do not work well when the regression error...
متن کاملAsymptotic Properties of Least Squares Estimators of Cointegrating Vectors
Time series variables that stochastically trend together form a cointegrated system. In such systems, certain linear combinations of contemporaneous values of these variables have a lower order of integration than does each variable considered individually. These linear combinations are given by cointegrating vectors. OLS and NLS estimators of the parameters of a cointegrating vector are shown ...
متن کاملSemiparametrically Modified OLS and IV Estimators for Linear Cointegrating Models
This paper proposes a semiparametrically modified OLS (SM-OLS) estimator and a semiparametrically modified IV (SM-IV) estimator via kernel method for linear cointegrating models when cointegrating equilibrium errors respond instantaneously to changes of the first-differenced integrated regressor in the linear cointegrating models. Both the proposed estimators are shown to have a mixed normal li...
متن کاملBootstrapping Cointegrating Regressions1
In this paper, we consider bootstrapping cointegrating regressions. It is shown that the method of bootstrap, if properly implemented, generally yields consistent estimators and test statistics for cointegrating regressions. We do not assume any speci ̄c data generating process, and employ the sieve bootstrap based on the approximated ̄nite-order vector autoregressions for the regression errors ...
متن کامل