This article focuses on a bivariate cointegrating model with non-normal errors. In particular, we propose a bivariate error distribution constructed using two non-identical marginals through a copula. The model parameters are estimated using the method of inference functions for margins and maximum likelihood. Applications of the proposed model are illustrated through real life examples.
CherubiniULucianoEVecchiatoW. Copula methods in finance. New York, NY: John Wiley & Sons; 2004.
2.
ChenXFanY. Estimation of copula-based semiparametric time series models. Econom. 2006; 130(2): 307–335.
3.
LeeTHLongX. Copula-based multivariate garch model with uncorrelated dependent errors. J Econom. 2009; 150(2): 207–218.
4.
ScailletOFermanianJD. Nonparametric estimation of copulas for time series; FAME Research paper 57. 2002.
5.
SklarM. Random variables, joint distribution functions, and copulas. Kybernetika. 1973; 9(6): 449–460.
6.
JoeHXuJ. The estimation method of inference functions for margins for multivariate models; Technical Report No. 166, Department of Statistics, University of British Columbia, Vancouver; 2016.
7.
ChorośBIbragimovRPermiakovaE. Copula estimation. In: JaworskiPDuranteFHaerdleWKRychlikT editors. Copula Theory and its Applications. Berlin/Heidelberg: Springer; 77–91.
8.
EngleRFGrangerCW. Co-integration and error correction: representation, estimation, and testing. Econometrica. 1987; 55(2): 251–276.
9.
KruskalWH. Ordinal measures of association. J Am Stat Assoc. 1958; 53(284): 814–861.
10.
XuJJ. Statistical modelling and inference for multivariate and longitudinal discrete response data. PhD thesis, University of British Columbia; 1996.
11.
BarnardG. The theory and applications of statistical inference functions. Lecture notes in statistics 44-dl mcleish, cg small. Metrika. 1991; 38: 249–250.
