Logo IMG
HOME > PAST ISSUE > Article Detail


To Throw Away Data: Plagiarism as a Statistical Crime

Whether data are numerical or narrative, removing them from their context represents an act of plagiarism

Andrew Gelman, Thomas Basbøll

Decoupling Story and Source

To see more clearly how plagiarism is a crime against statistics, we need to examine how it helps to decouple the story from the source. In Weick’s case, this distancing allowed him to convey a message that was virtually the opposite of the story’s original meaning. Weick first told the story in 1982 when, five years after the appearance of Holub’s poem, Robert Swieringa and he published an article in the Journal of Accounting Research including a nearly word-for-word transcription of the poem text, but not using quotation marks or acknowledging Holub at all. In a 1987 essay, Weick added a “twist” to the story that had resulted from a conversation with Robert Engel, a Wall Street executive. Engel, he relates, suggested the possibility that the leader who was out with the troops might have known that the map was false and still used it effectively. Weick concurs with Engel and expounds on the implications as follows:

What is interesting about Engel’s twist to the story is that he has described the basic situation that most leaders face. Followers are often lost and even the leader is not sure where to go. All the leader knows is that the plan or the map he has in front of him is not sufficient by itself to get them out. What he has to do, when faced with this situation, is instill some confidence in people, get them moving in some general direction, and be sure they look closely at what actually happens, so that they learn where they were and get some better idea of where they are and where they want to be.

He goes on to suggest that the key in this kind of situation is to “get people moving.” But in Holub’s poem—Weick’s primary source material—the soldiers’ recounting stands in direct opposition to this interpretation: They say that the map “calmed us down” and that they “pitched camp, lasted out the snowstorm.”

Making speculations about what might have happened differently in a situation is not an invalid strategy in all settings; it’s just a nonempirical one. In this case the line between fact and supposition was blurred so badly that no such distinction could be made. But facts exist that can be adduced to determine whether Engel’s supposition was correct. Assuming that any such event actually occurred, then his notion about what happened is either right or wrong. As it turns out, versions of the story that predate Holub’s poem appear in reports given by medical researchers Oscar Hechter and Bernard Pullman at scientific symposia in the early 1970s. These versions suggest that the anecdote as told by Szent-Gyorgyi had the troops’ immediate leader thinking it was a map of the Alps, too. Those versions rule out Engel’s interpretation.

That interpretation may, of course, be more appealing to Wall Street executives. Given the evolution of modern finance since the mid-1980s, the fact that they appear to have thought that “any old map will do” is somewhat disturbing. But Engel’s idea was generated in a problematic context, one in which Weick had, in effect, taken ownership of the story and arrogated for himself the right to alter it at will. The act of plagiarism was the first step in a process that unmoored the story from its sources and removed its evidential value.

» Post Comment



Subscribe to American Scientist