Premium
The Place of Multiple Regression Analysis in Modern Approaches to Disease Control 1)
Author(s) -
ROYLE D.J.,
Burr D.J.
Publication year - 1979
Publication title -
eppo bulletin
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.327
H-Index - 36
eISSN - 1365-2338
pISSN - 0250-8052
DOI - 10.1111/j.1365-2338.1979.tb02247.x
Subject(s) - regression analysis , regression , simplicity , computer science , context (archaeology) , regression diagnostic , interpretation (philosophy) , plant disease , disease , value (mathematics) , machine learning , artificial intelligence , polynomial regression , statistics , mathematics , biology , epistemology , medicine , philosophy , microbiology and biotechnology , pathology , programming language , paleontology
In this paper multiple regression models are compared with fundamental models in the context of the plant disease system. The value of the regression technique for analysing the pathogen–host–environment complex and for prediction is discussed. Although there are limitations to the use and interpretation of multiple regression equations, their underlying simplicity can be of advantage for the solution of many practical problems in disease management. Despite the empirical nature of multiple regression, it can be used to advantage in the construction of hybrid models of the deductive–inductive type which combine the summary of experience with the fundamental principles of disease mechanisms.