Premium
Principal predictors
Author(s) -
Thacker W.C.
Publication year - 1999
Publication title -
international journal of climatology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.58
H-Index - 166
eISSN - 1097-0088
pISSN - 0899-8418
DOI - 10.1002/(sici)1097-0088(19990630)19:8<821::aid-joc390>3.0.co;2-o
Subject(s) - principal component analysis , canonical correlation , context (archaeology) , principal (computer security) , set (abstract data type) , climatology , econometrics , mathematics , statistics , computer science , geography , geology , archaeology , programming language , operating system
Principal predictors are linear combinations of variables from one set that efficiently describe the collective variability of those from a second set. Their defining eigenproblem is similar to that of canonical correlation analysis, and when the two sets are taken to be the same, principal predictors reduce to principal components. Within the context of a forecast model for the circulation in the Gulf of St. Lawrence, they are shown to be capable of providing a low‐dimensional characterization of high‐resolution model dynamics.