Premium
Detecting Changes in Ecological Time Series
Author(s) -
Jassby Alan D.,
Powell Thomas M.
Publication year - 1990
Publication title -
ecology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.144
H-Index - 294
eISSN - 1939-9170
pISSN - 0012-9658
DOI - 10.2307/1938618
Subject(s) - causation , series (stratigraphy) , ecology , principal component analysis , flexibility (engineering) , time series , computer science , mathematics , statistics , artificial intelligence , machine learning , biology , epistemology , paleontology , philosophy
Some practical techniques are discussed for analyzing time series whose statistical properties are changing with time. We first consider how principal component analysis can reduce the multidimensional nature of certain series and, in particular, apply this technique to the analysis of changing seasonal patterns. Discussions of trend, changes in oscillatory behavior, and unusual events follow. The problem of making inferences regarding causation is briefly considered. We conclude with a call for flexibility in approach.