Author： Chen Wen-Den
Publisher： Taylor & Francis Ltd
ISSN： 1360-0532
Source： Journal of Applied Statistics, Vol.33, Iss.8, 2006-09, pp. : 759-772
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
This article shows a test for the spurious regression problem in a panel data model with a growing individual number and time series length. In the estimation, tapers are used and the integrated order for the remainder disturbance is extended to a real number; at the same time, the spurious regression problem can be detected without prior knowledge. Through Monte Carlo experiments, we examine the consistent estimators by various sizes of time length and individual number, in which the remainder disturbance is assumed to be either stationary or non-stationary. In addition, the asymptotic normality properties are discussed with a quasi log-likelihood function. From the power tests we can see that the estimators are quite successful and powerful.
Related content
Access to resources
Recommend
Testing for normality with panel data
Journal of Statistical Computation and Simulation, Vol. 81, Iss. 11, 2011-11 ,pp. :