Judging by the following notes in my ~/jot directory, I was inspired two years ago (Oct 23, 2013) by a TEDx talk by Josh Kaufman on learning:

Josh’s advice boils down to 4 major points:

  1. Deconstruct the skill.
  2. Learn enough to self-correct (don’t procrastinate by reading text-books).
  3. Remove practice barriers (distractions).
  4. Practice for at least 20 hours. [This is the gist of his talk, but I guess it is a complitely arbitrary out-of-his-ass thing.]

Perhaps I could apply this approach to figuring out which statistical model(s) to use for the peat moss fluorescence data which I’ve been struggling with these past few weeks. Since I don’t have a statistics text-book, I can’t exercise my love of text-book-aided procrastination, a shortcoming which I’ve compensated by my old debugging procrastination strategy—just fiddling around until something useful happens. Sadly, it is becoming apparent to me that with statistics, nothing useful is learned if you don’t understand what you’re doing and why. :'(