Author:
Panov Vladimir Grigorievich
Abstract
The problem of establishing a relationship between linear statistical models with the same response, but with different sets of predictors, is considered. It is shown that the parameters of the considered models turn out to be connected by linear matrix equalities, in which the parameters of linear models connecting different sets of predictors participate.
Reference16 articles.
1. Seber G.A.F. and Lee A.J. Linear regression analysis. - New York: John Wiley& Sons Inc., 2003. - 581 p.
2. Ayvazian S.A., Yeniukov I.S., Meshalkin L.D. Applied statistics. Investigation of dependencies. - Moscow: Finance & Statistics, 1985. - 488 p. (in Russian).
3. Cook R.D., Weisberg S. An Introduction to Regression Graphics. - New York: John Wiley& Sons Inc., 1994. - 243 p.
4. Kutner M.H., Nachtsheim C.J., Neter J., Li W. Applied linear statistical models. - McGraw-Hill/Irwin, 2005. - 1394 p.
5. Draper N., Smith H. Applied regression analysis (Wiley Series in Probability and Statistics) - Hoboken: John Wiley& Sons Inc., 1998. - 736 p.