As a regular instructor of Statistics and Social Research classes, I took note at this paragraph in a recent profile of Bruno Latour:

Latour believes that if scientists were transparent about how science really functions — as a process in which people, politics, institutions, peer review and so forth all play their parts — they would be in a stronger position to convince people of their claims. Climatologists, he says, must recognize that, as nature’s designated representatives, they have always been political actors, and that they are now combatants in a war whose outcome will have planetary ramifications. We would be in a much better situation, he has told scientists, if they stopped pretending that “the others” — the climate-change deniers — “are the ones engaged in politics and that you are engaged ‘only in science.’ ” In certain respects, new efforts like the March for Science, which has sought to underscore the indispensable role that science plays (or ought to play) in policy decisions, and groups like 314 Action, which are supporting the campaigns of scientists and engineers running for public office, represent an important if belated acknowledgment from today’s scientists that they need, as one of the March’s slogans put it, to step out of the lab and into the streets. (To this Latour might add that the lab has never been truly separate from the streets; that it seems to be is merely a result of scientific culture’s attempt to pass itself off as above the fray.)

Textbooks on Statistics and Social Research say there are right ways and wrong ways to do the work. There are steps to follow, guidelines to adhere to, clear cut answers on how to do the work right. It is all presented in a logical and consistent format.

There are hints that this may not happen all the time. Certain known factors as well as unknown issues can push a researcher off track a bit. But, to do a good job, to do work that is scientifically interesting and acceptable to the scientific community, you would want to stick to the guidelines as much as possible.

This provides a Weberian ideal type of how science should operate. Or, perhaps the opposite ideal type occasionally provides a contrast. The researcher who committed outright fraud. The scholar who stepped way over ethical boundaries.

I see one of my jobs of teaching these classes as providing how these steps work out in actuality. You want to follow those guidelines but here is what can often happen. I regularly talk about the constraints of time and money: researchers often want to answer big questions with ideal data and that does not always happen. You make mistakes, such as in collecting data or analyzing results. You send the manuscript off for review and people offer all sorts of suggestions of how to fix it. The focus of the project and the hypothesis changes, perhaps even multiple times. It takes years to see everything through to publication.

On one hand, students often want the black and white presentation because it offers clear guidelines. If this happens, do this. On the other hand, presenting the cleaner version is an incomplete education into how research works. Students need to know how to respond when the process does not go as planned and know that this does not necessarily mean their work is doomed.

Scientific research is not easy nor is it always clear cut. Coming back to the ideal type concept, perhaps we should present it as we aspire to certain standards and particular matters may be non-negotiable but there are parts of the process, sometimes small and sometimes large, that are more flexible depending on circumstances.