Poster Paper:
What Is Evidence-Based Research?
*Names in bold indicate Presenter
What Is Evidence-Based Research?
Classical statistics emphasizes minimizing Type I errors, whereas Evidence-Based Research (EBR) emphasizes minimizing Type II errors. The different emphasis is profound. In Evidence-based medicine (EBM), EBR's parent, this means erring on the side of not rejecting a treatment that could help patients, instead of erring on the side of refusing to accept a treatment that might not work.
The cited successes of EBR are all EBM. Policy research is intrinsically different from EBM. In EBM, only one parameter, such a medication dosage, is modified at a time. No human interaction is involved, nothing about whether the subject likes the treatment. In the Policy realm, though, everything is part of a system, and changing one parameter alters at least one more, which may even be the subjects' approval of the change. EBM is also blinded, so that the researchers and subjects are unaware of each subject's treatment. In policy research, though, since subjects live the changes, they are aware. EBM also considers the ethics of a treatment, and how this affects subjects.
Good policy research does provide real evidence, just not the EBR type of evidence. I can see why the President favors EBR, for how can one not want to base policy on evidence? It is just that plain old statistical research is what is called for when analyzing Public Policy data.
Some references:
Guyatt, Gordon and Rennie, Drummond, editors. Users' Guides to the Medical Literature: Essentials
of Evidence-Based Clinical Practice, AMA Press, 2004.
Liebman, Jeffrey B. “Building on Recent Advances in Evidence-Based Policymaking.” Harvard
University, NBER, April 2013.
Mathis, W. J. (2010). The “Common Core” Standards Initiative: An Effective Reform Tool? Boulder
and Tempe: Education and the Public Interest Center & Education Policy Research Unit. Retrieved
April 9, 2015 from http://epicpolicy.org/publication/common-core-standards.
