Premium
SOME REPARAMETERIZATIONS OF LAG POLYNOMIALS FOR DYNAMIC ANALYSIS
Author(s) -
Burke Simon P.
Publication year - 1996
Publication title -
oxford bulletin of economics and statistics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.131
H-Index - 73
eISSN - 1468-0084
pISSN - 0305-9049
DOI - 10.1111/j.1468-0084.1996.mp58002009.x
Subject(s) - univariate , autoregressive model , multivariate statistics , scalar (mathematics) , mathematics , cointegration , representation (politics) , polynomial , context (archaeology) , lag , orthogonal polynomials , econometrics , series (stratigraphy) , distributed lag , statistics , pure mathematics , mathematical analysis , computer science , paleontology , computer network , geometry , politics , political science , law , biology
Various reparameterizations of scalar polynomials are considered in the context of lag polynomials. These are used to explore possibilities of testing for stationary autoregressive roots, repeated roots, and polynomial factors of given form. Multivariate generalizations of these results are then applied to VAR models and to comovement between the component series of such systems. The link between the representation of unitroots in the univariate case and cointegration in multivariate systems is demonstrated.