Plane answers to complex questions

Mehr zum Buch

This textbook offers a comprehensive introduction to the theory and application of linear models for data analysis. The author focuses on a unified approach to linear models, covering analysis of variance and regression models through concepts like projections and orthogonality. Each chapter features numerous exercises and examples, making it suitable for graduate-level courses. Key topics are explored in depth, including ANOVA, Bayesian estimation, hypothesis testing, multiple comparisons, regression analysis, and experimental design. Additionally, it addresses advanced topics often overlooked at this level, such as balanced incomplete block designs, testing for lack of fit, independence testing, singular covariance matrices, variance component estimation, best linear and best linear unbiased prediction, collinearity, and variable selection. The new edition introduces discussions on identifiability and estimability, various theories for testing parametric hypotheses and analysis of covariance, the geometry of least squares estimation, models for factorial treatment structures, and an appendix on potential causes for unusually small test statistics. Ronald Christensen, a Professor of Statistics at the University of New Mexico, is a Fellow of the American Statistical Association and the Institute of Mathematical Statistics.