This text is a new and improved edition of Rawlings (1988). It is the outgrowth
of several years of teaching an applied regression course to graduate
students in the sciences. Most of the students in these classes had taken
a two-semester introduction to statistical methods that included experimental
design and multiple regression at the level provided in texts such
as Steel, Torrie, and Dickey (1997) and Snedecor and Cochran (1989). For
most, the multiple regression had been presented in matrix notation.
The basic purpose of the course and this text is to develop an understanding
of least squares and related statistical methods without becoming excessively
mathematical. The emphasis is on regression concepts, rather than on
mathematical proofs. Proofs are given only to develop facility with matrix
algebra and comprehension of mathematical relationships. Good students,
even though they may not have strong mathematical backgrounds, quickly
grasp the essential concepts and appreciate the enhanced understanding.
The learning process is reinforced with continuous use of numerical examples
throughout the text and with several case studies. Some numerical
and mathematical exercises are included to whet the appetite of graduate
students.