This book presents a unified theory of inference from linear models with minimal assumptions. It serves as a graduate-level text for statistics courses and an accompanying text for courses where linear models are integral. The authors detail both least squares theory and alternative methods for estimation and testing, utilizing convex loss functions and general estimating equations.

This text is recognized for its comprehensive and unified approach to linear models, making it a valuable resource for advanced statistics students and researchers. Its rigorous treatment of estimation and testing methods, particularly the inclusion of alternatives to least squares, is noted for its theoretical depth. The book is structured to facilitate understanding for those already familiar with foundational statistical concepts. Its utility extends to various disciplines that rely on the application of linear models.