A common break in means for long-range dependent panel data under cross-sectional independence
This paper focuses on estimating a common break point in means for long-range depen-dent panel data under cross-sectional independence.The common break-point estimator is examined under three scenarios:strong,moderate and weak break signals.Asymptotic properties,including consistency,rate of convergence and limiting distribution,of the estimator are established.The theo-retical results reveal that there is a trade-offbetween the break signal and long-range dependence.To be more precise,the long-range dependence has no ability to influence the asymptotic behaviors of the estimator if the break signal is strong,it does not influence the rate of convergence but has an impact on the limiting distribution of the estimator when the break signal is moderate,and it influences both the rate of convergence and the limiting distribution of the estimator when the break signal is weak.Monte Carlo simulations are conducted to assess the finite-sample performance of the estimator,and the theoretical results are supported by the simulation results.
common breaklimiting distributionlong-range dependencepanel data
万方数据
维普
