Doing (applied) mathematical research is a little bit like walking through the woods: sometimes I get stuck and have to work around an obstacle, and I usually don’t end up exactly where I intend to go, but I usually make some progress. And in many cases the math is smarter than I am, in the sense that, through mathematical analysis, I’m able to find a correct answer that is surprising, until I realize how truly right it is.
That is Andrew Gelman on mathematical research.
Guillermina Jasso had a remark at a recent conference, when she said: “Say it it math, because if you can not say in math, you probably did not understand your point.” If I would need atribute the two lines of thinking, Gelman (as a statguy doing pol-econ) probably is more close to an economist and Jasso’s claim sounds more like a sociologist, thus the field she represents. I much prefer the latter, although I would not imply that economist think “modelling comes first, reasoning comes second”. But it truly reflects the line of thinking drawn from physics which obviously not the only way one can approach social science research (think of Menger, Veblen, Vanberg).