Measuring correlations of integrated but not cointegrated variables: A semiparametric approach

• Published in: Journal of econometrics Vol. 164; no. 2; pp. 252 - 267
• Main Authors: Sun, Yiguo, Hsiao, Cheng, Li, Qi
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.10.2011; Elsevier; Elsevier Sequoia S.A
• Series: Journal of Econometrics
• Subjects: Applications; Cointegration; Cointegration analysis; Correlation analysis; Econometric models; Econometrics; Estimation; Exact sciences and technology; Inference from stochastic processes; time series analysis; Insurance, economics, finance; Integrated time series; Integrated time series Non-cointegration Semiparametric varying coefficient models; Macroeconomics; Mathematics; Multivariate analysis; Non-cointegration; Probability and statistics; Sciences and techniques of general use; Semiparametric varying coefficient models; Simulation; Statistics; Studies; Time series; Unit root; Vector-autoregressive models; C20; Semiparametric varying coefficient models; Non-cointegration; C13; Integrated time series; C14; Correlation; Finance; Time series; Finite sample; Statistical association; Statistical estimation; Multivariate analysis; Semiparametric method; Stochastic process; Semiparametric model; Statistical method; Simulation; Correlation analysis; Cointegration; Consistent estimator; Autocorrelation; Econometrics
• ISSN: 0304-4076; 1872-6895
• DOI: 10.1016/j.jeconom.2011.05.013

Many macroeconomic and financial variables are integrated of order one (or I ( 1 ) ) processes and are correlated with each other but not necessarily cointegrated. In this paper, we propose to use a semiparametric varying coefficient approach to model/capture such correlations. We propose two consistent estimators to study the dependence relationship among some integrated but not cointegrated time series variables. Simulations are used to examine the finite sample performances of the proposed estimators.