Revisions: Emphasis

As in earlier editions, I have made a concerted effort to point out what kinds of questions can legitimately be answered by the statistical analyses considered in this book. In this edition, however, I try even harder to show that there is often a difference--and sometimes a giant difference--between what researchers are entitled to say following their data analyses and what they actually do say. My concern about this shows up throughout the many chapters concerned with inferential techniques. Of this book's 21 chapters, 15 deal with statistical procedures that bring forth claims of "significance" or "significant differences." Such procedures inherently involve sample-to-population inferences, null hypotheses, underlying assumptions, the possibility of inferential error, and "significance" that may exist in a statistical sense but not in any practical manner. I have purposefully emphasized these facets of statistical analysis more here than in the second edition, for it is my growing observation that applied researchers often forget about inference and instead reify their sample statistics into population parameters.

(Click here to see a passage from the book where emphasis is placed on the important distinction between statistical significance and practical significance.)

I have also tried my best to assert at every opportunity that complex statistics do not have the magical power to create a silk purse out of a sow's ear. Unless the research questions being addressed are worthy, a study is doomed from the start. Accordingly, there is more emphasis here than before on critically evaluating research questions and null hypotheses as the first step in assessing the potential value of any investigation.

(Click here to see a passage from the book where emphasis is placed on the importance of the null hypothesis.)

Finally, I have made an effort in this edition to describe more fully a larger number of the studies that have supplied excerpts. Many of these studies dealt with important questions, were designed thoughtfully, and produced findings that may impact the way people think or act. Other studies focused on topics that were undoubtedly fun for the researchers to research. By considering the research questions and methodology associated with these studies, perhaps more than a few readers will adopt the view that research can be both fun and relevant to their daily lives.

(Click here to see a sample description of a study connected to one of the book's excerpts.)

Copyright © 2003 Schuyler W. Huck
All rights reserved.