Om att gå vilse bland siffror

Once upon a time, statisticans only explored. Then they learned to confirm exactly—to confirm a few things exactly, each under very specific circumstances. As they emphasized exact confirmation, their techniques with past insights became less flexible. The connection of the most used techniques with past insights was weakened. Anything to which a confirmatory procedure was not explicitly attached was decried as »mere descriptive statistics«, no matter how much we had learned from it.

John Wilder Tukey, Exploratory Data Analysis (Reading, MA: Addison-Wesley, 1977).