> My book is > Statistical Analysis and Data Display, Richard M. Heiberger, Burt > Holland, 2nd ed. 2015
In all fairness, I thought should look at your book. I was quite impressed by the chapter on multiple comparisons. And may look again, later. In my personal opinion (diverging slightly), with more and more people using extensive exploratory-style modelling, I think some of the methods for multiple comparisons could (and should) be adapted to the interpretation of exploratory plots. And returning to your book... There's relatively comprehensive chapters on multiple regression. And I'm happy you used the term "explanatory" rather than "independent". When people use the term "independent variables" (outside a theoretical context) they usually go my how-did-these people-get-a-job list. Some comments: (1) Expanding on the above point, I couldn't see a section on interpreting regression coefficients, which is something people often get wrong. (2) It had a nice objective/frequentist flavor, but it would have been nicer to see clearer references to robust, semiparametric and more general nonparametric methods, even if only brief. In principle, some of these (but not all) follow the same philosophy as classical statistics, but allow greater flexibility. ______________________________________________ R-help@r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
