Wednesday, December 15, 2010

Sherlock Holmes and Working with No Data

I came across this great quote from Sherlock Holmes (via Arthur Conan Doyle, The Adventures of Sherlock Holmes, "A Scandal in Bohemia") that aptly describes the dangers of speculating, theorizing, and developing conclusions before we have enough data to base them on. Holmes has received an unusual letter and shared it with Dr. Watson. Here is their exchange:
"This is indeed a mystery," I remarked. "What do you imagine that it means?"
"I have no data yet. It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts...."

Ever read a scholarly argument passionately demonstrating how the data are not, in fact, in conflict with the theory, despite appearances?

Posted by at
Labels: , , ,

4 comments:

  1. RichBDecember 16, 2010 at 9:03 AM

    Uncle!

    ReplyDelete
  2. AnonymousDecember 17, 2010 at 6:01 AM

    But... what do we then do with this?

    http://www.eisenbrauns.com/item/GOLWORKIN

    ReplyDelete
  3. Douglas MangumDecember 17, 2010 at 8:23 AM

    I see you've identified my title's allusion to Lambdin's famous saying.

    The challenge in our field(s) is walking that line between having enough data to make a judgment and never having all the data.

    The problem that is more common, IMO, is that all too often the theory, not the data, is in the driver's seat. Cart before horse and all that.

    ReplyDelete
  4. Seth SandersDecember 26, 2010 at 8:19 AM

    "walking that line between having enough data to make a judgment and never having all the data." --good line, Doug!

    Seth

    ReplyDelete

Subscribe to: Post Comments (Atom)