Skip to content
 

God is in every leaf of every tree

In a recent article in the New York Review of Books, Freeman Dyson quotes Richard Feyman:

No problem is too small or too trivial if we really do something about it.

This reminds me of the saying, “God is in every leaf of every tree,” which I think applies to statistics in that, whenever I work on any serious problem in a serious way, I find myself quickly thrust to the boundaries of what existing statistical methods can do. Which is good news for statistical researchers, in that we can just try to work on interesting problems and the new theory/methods will be motivated as needed. I could give a zillion examples of times when I’ve thought, hey, a simple logistic regression (or whatever) will do the trick, and before I know it, I realize that nothing off-the-shelf will work. Not that I can always come up with a clean solution (see here for something pretty messy). But that’s the point–doing even a simple problem right is just about never simple. Even with our work on serial dilution assays, which is I think the cleanest thing I’ve ever done, it took us about 2 years to get the model set up correctly.

As the saying goes, anything worth doing is worth doing shittily.

2 Comments

  1. Jav says:

    Nice blog and many thanks for the pointer to Dyson's article.

  2. briang says:

    This reminds me of something that always bothered me in my sociology stats courses. Why in the social sciences do we think our simplistic methods can answer very complex questions social scientists often ask? How can regression and p values (http://www.epidem.com/pt/re/epidemiology/pdfhandler.00001648-200105000-00005.pdf;jsessionid=DOGHsvvFfOPYSByEa4JB21AHNq2Dzpidu0nzRzeXK48XnUvkpXEB!-365670234!-949856145!9001!-1) be of any use. Physists ask much simpler questions than social scientists, yet sociologists seem fine with knowing nothing more than algebra and a black box stats program like spss, where physists know almost enough math to be mathematicians. Epidemiologists have been advancing our methods more than we have. Why are the few quantative sociologists treated as "those people"? Epidemiolgists have done more with factor analysis and SEM than us. Epidemiolgists ask questions no more difficult than us, yet they have to at least take calculus (the real calculus course not this BS cal for business and soc sci). Sociologists need to look at what the epidemiolgists are doing. ie Higher dimensional analysis, CART, random forests, etc (http://www.springerlink.com/(q4ma523rbpftpn55g21x2yih)/app/home/contribution.asp?referrer=parent&backto=issue,1,5;journal,33,139;linkingpublicationresults,1:100309,1). I am tired of reading and hearing the same crap every year from sociology (ASA conferences and journals)- it ought not be a discipline to have a soapbox for you political view, but should be a venue to share your scientific knowledge. Re-hashing (and getting it wrong and not giving Engels his due) Marxist philosophy is really getting us no where, and if sociology cares about people then we ought to do more science and less 'talking out our ass political BS!'