THE RELATION BETWEEN REGRESSION COEFFICIENTS IN A MULTIPLE-REGRESSION ANALYSIS
Author(s) -
J. E. Monahan
Publication year - 1959
Publication title -
osti oai (u.s. department of energy office of scientific and technical information)
Language(s) - English
Resource type - Reports
DOI - 10.2172/4203324
Subject(s) - mathematics , simple linear regression , statistics , regression analysis , simple (philosophy) , regression , linear regression , value (mathematics) , proper linear model , segmented regression , regression diagnostic , standardized coefficient , polynomial regression , regression dilution , relation (database) , computer science , data mining , philosophy , epistemology
In a multiple-regression analysis it is often necessary to assign a value, different from the least-squares value, to one or more of the regression coefficients. A simple method is described which eliminates the matrix algebra which, in such cases, is usually necessary in order to re-evaluate the remaining coeffcients, together with the associated variances and covariancesThe method is generalized to give an equally simple procedure for testing possible linear relations among the regression coefficients. (auth
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom