What question did this study set out to answer?

To evaluate and compare the performance of ordinary and symmetric least squares estimators alongside their associated unit root tests in second-order autoregressive processes.

July 1, 1995Journal of Time Series Analysis

Alternative Estimators and Unit Root Tests for the Autoregressive Process

View Full Paper

Ask AI

Bookmark

Authors

HPHeon Jin ParkSAS Institute (United States)WFWayne A. FullerIowa State University

Discussion

Member takes

Implication

Simulation study reveals superior power for weighted symmetric least squares in autoregressive models with estimated intercepts, highlighting optimal estimators for unit root testing.

Key Points

To evaluate and compare the performance of ordinary and symmetric least squares estimators alongside their associated unit root tests in second-order autoregressive processes.
Conducted Monte Carlo simulations across second-order autoregressive models to evaluate estimator accuracy and unit root test power.
Compared three parameter estimation techniques: ordinary least squares, simple symmetric least squares, and weighted symmetric least squares.
Weighted symmetric least squares estimators generally achieved smaller mean square errors than ordinary least squares, especially when one root approached one in absolute value.
For second-order models with a known zero intercept, the one-sided ordinary least squares unit root test exhibited higher statistical power than the symmetric alternatives.
For models requiring an estimated intercept, the one-sided weighted symmetric least squares test demonstrated the highest statistical power among all evaluated tests.

Cite This Study

Park et al. (1995) studied this question.

synapsesocial.com/papers/6a0ec5332eca052da647c50a https://doi.org/10.1111/j.1467-9892.1995.tb00243.x

View Full Paper

Ask AI

Bookmark

Implication

Simulation study reveals superior power for weighted symmetric least squares in autoregressive models with estimated intercepts, highlighting optimal estimators for unit root testing.

Alternative Estimators and Unit Root Tests for the Autoregressive Process

Discussion

Member takes

Implication

Key Points

Cite This Study

Alternative Estimators and Unit Root Tests for the Autoregressive Process

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider