Premium
Identification of Time Series with Infinite Variance
Author(s) -
Rosenfeld Gerald
Publication year - 1976
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2346683
Subject(s) - identification (biology) , series (stratigraphy) , variance (accounting) , mathematics , statistics , geology , biology , economics , paleontology , botany , accounting
Summary The effects of infinite variance random shocks on the identification of time series models is studied. Identifying functions are computed and then compared with the known structures of computer simulated series. A data clipping method to improve identification is examined. It is asserted that the Box‐Jenkins methods for identifying time series are still useful, in conjunction with data clipping, even in the presence of infinite variance.