An Invariant Approach to Statistical Analysis of Shapes

The webpage cited in the text contains all of the large datasets presented, a table of contents, answers to selected exercises, miscellaneous links, and the computer code used in Appendix C. I found the material reasonable, but would have liked to have seen the R code for additional case studies worked out to the same extent as the case study in Appendix C. I felt there were other techniques used sufficiently often throughout the text that some exemplary code, either on the webpage or the Appendix, would have been appropriate. In particular, the EM algorithm is used repeatedly in the latter half of the book, but no code implementing EM methods is provided. Granted, the EM steps are spelled out in some detail in numerous places in the book, but some typical code would be useful. In an ambitious work such as this, it is easy to find ways in which the material could be reorganized, and suggestions for reorganization necessarily depend on what the user has in mind. With that caveat, I think the material in the very last chapter could be incorporated, or at least integrated, into either Chapter 6 or Chapter 11. The transition between the discussion of Bayesian decision analysis in Chapter 23 and posterior inference in those other chapters is essentially seamless and could be easily incorporated into the authors’ analysis rubric presented in Chapter 11. This is a book that challenges the user in its sophisticated approach toward data analysis in general and Bayesian methods in particular. I am thoroughly excited to have this book in hand to supplement course material and to offer research collaborators and clients at our consulting lab more sophisticated methods to solve their research problems.