The problem with real-world experiments is, sometimes, they involve the real world. And the real world doesn't often fully, um, appreciate your efforts. Case in point, this political research study (via colleague Karen Russell). I may add my own comments later.
I posted this to one of my listervs (AAPORNet), which is made up of folks who do political polling and public opinion research, and asked if anyone had any thoughts about it or knew much about it. Instantly had 93 hits on the link, but not a single response on the listserv. So far.
Now up to 270 clicks, though some from another listserv of data journalists. Also links to responses to this that ably criticize the criticism of the field experiment.