數(shù)據(jù)造假新手段“P值黑客”

如今，在科學(xué)研究中，出現(xiàn)了比學(xué)術(shù)欺詐更令人擔(dān)憂發(fā)指的行為——P值黑客(P-hacking)。

P-hacking refers to the practice of manipulating scientific data so that the results appear to be statistically significant.
“P值黑客”是指操作科學(xué)數(shù)據(jù)，從而使結(jié)果看上去具有統(tǒng)計(jì)學(xué)意義的行為。

這個詞最早由賓夕法尼亞大學(xué)的西蒙松教授提出，一起來看看他是怎么說的：

Professor Uri Simonsohn of UPenn discussed what he refers to as "p-hacking." P-hacking is the idea that if researchers are engaging in questionable analysis practices, then they should have a disproportionate number of findings at or close to the p < .05 threshold for statistical significance, and that this can be relatively easy to detect.
賓夕法尼亞大學(xué)西蒙松教授談到他所指的P值黑客。P值黑客是指如果研究人員采用的分析方法可疑，那么他們應(yīng)當(dāng)有一個不成比例的P值數(shù)據(jù)結(jié)果等于或接近p<0.05這個統(tǒng)計(jì)學(xué)意義閥值，而這也相對很容易被發(fā)現(xiàn)。

雖然直譯為“P值黑客”，但從定義上看，該詞有“數(shù)據(jù)造假”的意思，這點(diǎn)可以從《大西洋月刊》上的文章《自我修正的科學(xué)之謎》(The Myth of Self-Correcting Science)中的解釋得到佐證：

Almost more alarming than the few individuals committing academic fraud are the high percentage of researchers who admitted to more common questionable research practices, like post-hoc theorizing and data-fishing (sometimes referred to as p-hacking), in a recent study led by Leslie John.
近期由萊斯利·約翰主導(dǎo)的研究指出，比少數(shù)人的學(xué)術(shù)欺詐行為更令人擔(dān)憂的是，有很高比例的研究人員承認(rèn)他們的做法更普遍更不靠譜，如事后推理和數(shù)據(jù)造假(有時指P值黑客)。

（中國日報網(wǎng)英語點(diǎn)津 丁一）