PsycCRITIQUES - How to Make the Best of Your Data

“When you make a prediction, would you rather be correct or incorrect? If your answer is'correct,' then ODA [optimal data analysis] is the appropriate analytic methodology...” (p. xi). With this audacious, provocative opening statement, Paul Yarnold and Robert Soltysik set the stage for a revolutionary paradigm shift in statistical analysis. It is obvious that no one could rationally answer “no” to such a question—who would rather be incorrect than correct when making predictions? Why else would one make predictions in the first place, except in hopes of being as accurate as possible? Yet, as Yarnold and Soltysik emphasize, to make predictions using any statistical approach other than ODA (pronounced “oh-dah,” with the accent on the “oh”) is to employ a paradigm that does not intentionally maximize the accuracy of predictions.