<p>To specify: in posts #37 & #39, I am referring to how actual cross-admit battles may play out, not to the RP study itself per se. It’s confusing to say that the RP study “excludes ED students.” More accurately, I mean that the RP study excludes ED **as a factor for **students so that it is not (what the study calls) a “confounding factor.” That way the RP study can fairly determine the cross-admit battles between two ED schools with differential ED (enrollment) rates or even between one school with ED and another without. According to the RP study, they are comparable insofar as they are in “equilibrium,” which is what the study is trying to get at. In other words, in real life, it is difficult and impractical to measure cross-admit rates because of external factors (such as ED status). For example, to compare the real cross-admit rates between Duke RD students and Columbia/Penn RD students may be unfair because the former represents a higher percentage of the applicant pool than the latter. But the RP study’s statistical model controls for this and other “confounding factors” and adjusts accordingly.</p>
<p>[SSRN-A</a> Revealed Preference Ranking of U.S. Colleges and Universities by Christopher Avery, Mark Glickman, Caroline Hoxby, Andrew Metrick](<a href=“http://papers.ssrn.com/sol3/papers.cfm?abstract_id=601105]SSRN-A”>http://papers.ssrn.com/sol3/papers.cfm?abstract_id=601105)</p>