Description:
The classic edition of What If There Were No Significance Tests? highlights current statistical inference practices. Four areas are featured as essential for making inferences: sound judgment, meaningful research questions, relevant design, and assessing fit in multiple ways.
Review Quotes:
"What If There Were No Significance Tests was a book ahead of its time. ... It inspired me to start teaching statistics differently. ... It continues to have an impact on me. I return to it every time debates erupt about significance testing, confidence intervals, or statistical inference generally. Nearly two decades after its publication, many of its ideas still are not only timely, but in some cases, unsurpassed. If there is any book in psychology's methodological canon that deserves a classic republication, this is it." - Michael Smithson, the Australian National University, Australia
"The contributors are a "Who's Who" of specialists in a variety of statistical areas. The book provides a balanced account of one of the most controversial and important issues of data analysis in recent decades, and it has inspired countless important researches and articles on such topics as significance testing, estimation of effect sizes, and construction of confidence intervals. Instruction in statistics has, or should be, greatly influenced by this book." - Robert Grissom, San Francisco State University, USA
"The book remains the sourcebook for issues related to Null Hypothesis Significance Testing and its alternatives. ... This is the go-to book for information on significance testing and its ramifications. ... Strengths and limitations of significance testing are entertainingly described by leaders in methodology. The comments in the book are as relevant today as ever." - David P. Mackinnon, Arizona State University, USA