Premium
EDUCATION
Author(s) -
Ahlund Mikael C.,
Barksdale Hiram C.,
Hilliard Jimmy E.
Publication year - 1977
Publication title -
decision sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.238
H-Index - 108
eISSN - 1540-5915
pISSN - 0011-7315
DOI - 10.1111/j.1540-5915.1977.tb01116.x
Subject(s) - multivariate statistics , series (stratigraphy) , econometrics , coherence (philosophical gambling strategy) , computer science , sample (material) , time series , frequency domain , statistics , mathematics , paleontology , chemistry , chromatography , computer vision , biology
This paper illustrates how multivariate spectral analysis can be used to analyze complex, dynamic, business systems. Important temporal aspects of multiple time series are captured in the frequency domain by the coherence, phase, and gain statistics. A computer simulation of a time domain model produces sample results which demonstrate how the timing relations between two series can be reversed when the effects common to both series are partialled out. Finally, an empirical multivariate analysis of beef prices is used to determine the timing relations among prices at different levels of the production‐distribution system.