Emphasizing statistical interpretation of complex algebraic results, Sengupta (Indian Statistical Institute) and Jammalamadaka (statistics, University of California-Santa Barbara) develop the basic theory of linear models using the linear zero function and the principle of covariance adjustment. Geometric arguments are involved as needed, and a review of vector spaces and matrices is provided to make the treatment self-contained. Complex, matrix-algebraic methods, such as those used in the rank-deficient case, are replaced by statistical proofs that show the parallels with the simple linear model. Familiarity with statistical inference and linear algebra at the upper division or first-year graduate level is required. Mastery of algebra is not a prerequisite. Annotation ©2006 Book News, Inc., Portland, OR (booknews.com)
