Foundations of Time Series Analysis and Prediction Theory

discussion of the role of randomization. Finally, the book provides very few references to other literature on the analysis of covariance. A very nice feature is the exercises provided at the end of each chapter. Many of these include additional datasets. It would be useful to have an index of the datasets used in both the examples and the exercises and to have the data Ž les available electronically, perhaps at the CRC Press website. Given its numerous tables and graphs, the book is well laid out, but the legends on some graphs are very difŽ cult to interpret. Analysis of Messy Data contains much valuable information. I highly recommend it to any researcher who, in addition to randomly assigning experimental units to treatment combinations, takes measurements on properties of the units or their environments that can be used as covariates. It would be an especially valuable resource for graduate students being introduced to the analysis of such data.