-----BEGIN PGP SIGNED MESSAGE----- Hash: SHA1 On Sun, 5 Jun 2005 11:48:06 -0700 Lan Barnes <[EMAIL PROTECTED]> wrote:
[snip, r.e. data vs. anecdote] > > > Todd Walton <[EMAIL PROTECTED]> wrote: > > > > > This page: > > http://www.sysprog.net/quotdata.html > > > > says that it belongs to Frank Kotsonis, whoever that is. A nutritionist, and the head of research fro NutraSweet, Inc., who undoubtedly used this quote to dismiss studies he considered "... either seriously flawed or used to support unwarranted conclusions." Which perhaps bears directly on: > In medicine, which is where I got my original scientific grounding, > the case study is the fundamental unit of published observations. > There is a strict structure to a good case study. It's a far cry from > a patient testimonial (I still will listen to those, but with much > more caution). But case studies are important, and they're basically > anecdotal. > > Gather enough of them, and you have data. Data, pleural of Datum (part of the joke in the quote), literally "something given" from latin. According to Webster's Third Intl Unabridged Dictionary: Sense 1: a. something that is given either from being experientially encountered or from being admitted or assumed for specific purposes. a fact or principle granted or presented : something upon which an inference or an argument is based or from which an intellectual system of any sort is constructed b. material serving as a basis for discussion, inference, or determination of policy (Other sources - A collection of facts from which conclusions may be drawn. Factual information used as a basis for reasoning, discussion, or calculation. Information organized for analysis or used as the basis for decision making.) Sense 2: detailed information of any kind (Other sources - Information. Refers to raw facts, observations, measurements, numbers, and so on. Documented information or evidence of any kind.) So if you are willing to accept the second sense of data, yes, anecdotes are data. But if you insist on the first sense, you are not assured of having data no matter how many anecdotes you collect. Anecdotes can be data in the first sense only if collected in a systematic, impartial manner in order to avoid bias. You may collect a thousand anecdotes where a patient with condition X took drug A and survived, but if you don't know the effect on not taking the drug, you can draw no conclusion. Studies from which you can draw conclusions don't necessarily have to be randomized, blinded, and controlled, but case studies need carefully chosen controls in order to be meaningful. Dave Looney - -- Convenience and cost is temporary. Ideology is forever. - Gabriel Sechan -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.0 (GNU/Linux) iD8DBQFCo2SzZnDUcKSydkURAiMuAJoCYCJLrgWlEv/ObPmKlTNacs8ZbACfXE+s HRohoK2cQTaKbMr68GA4bV4= =YMw/ -----END PGP SIGNATURE----- -- [email protected] http://www.kernel-panic.org/cgi-bin/mailman/listinfo/kplug-list
