User talk:Aroehrig

Social science
Hi Aroehrig!

There is nothing wrong with social science. I have been happy to credit psychology with the invention of randomized experiments (citing Stephen Stigler), in numerous articles in Wikipedia, for example. I have written substantial portions of articles in education, political science (political sociology), economics, and related articles in history and gender-studies, etc.

That said, most "research methods for social scientists" books should be burned, voluntarily of course.

The text I reverted had several infelicities. One was the statement that the design of studies had several of wonderous properties, minimizing costs, maximizing information, etc. In fact, most studies (particularly in social science) are so bad that they should never have been done, according to Campbell & Cooke & Shadish.

In fact, most experiments are not optimal in any sense, and in fact the most popular textbook in the US used to have a bizarre attack against optimal designs (that did maximize information or minimize costs), according to the centenary article in Biometrika by Atkinson and Bailey. Almost all books on RSM emphasize designs that are known to be inefficient---an honorable exception being the exceptional (University of Michigan) textbook by C. Jeff Wu (now a Rambling Wreck!) and Hamada. Given these facts, a statement that DoE optimizes anything (especially two distinct criteria) is false, and appears as false advertising for DoE as a field. (Experts in DoE, especially researchers, probably can be described as optimizers in some sense, of course.)

Sincerely, Kiefer .Wolfowitz 19:44, 4 April 2012 (UTC)