Premium
LIMITATIONS ON THE USE OF THE MULTIPLE LINEAR REGRESSION MODEL
Author(s) -
MAXWELL A. E.
Publication year - 1975
Publication title -
british journal of mathematical and statistical psychology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 3.157
H-Index - 51
eISSN - 2044-8317
pISSN - 0007-1102
DOI - 10.1111/j.2044-8317.1975.tb00547.x
Subject(s) - proper linear model , linear regression , principal component regression , econometrics , regression , regression analysis , principal (computer security) , linear model , statistics , sampling (signal processing) , mathematics , computer science , bayesian multivariate linear regression , filter (signal processing) , computer vision , operating system
This paper discusses briefly the classic multiple linear regression model and indicates the principal ways in which its assumptions are inadequately met when it is used as a model for prediction purposes in the social sciences. It also considers the damping effects of errors of measurement and of selective sampling on estimates of partial regression and multiple correlation coefficients and describes techniques whereby these effects may in part be overcome.