Loading ...
Sorry, an error occurred while loading the content.

RE: [Synoptic-L] Counting Pericopes

Expand Messages
  • E Bruce Brooks
    To: Synoptic (GPG) In Response To: Bob Schacht On: Counting From: Bruce BOB: which is why we need means and standard deviations of appropriate samples to
    Message 1 of 9 , Aug 4 9:33 AM
    • 0 Attachment
      To: Synoptic (GPG)
      In Response To: Bob Schacht
      On: Counting
      From: Bruce

      BOB: which is why we need means and standard deviations of appropriate
      samples to explore the relationship between page size and pericope length. /
      BRUCE: Always assuming that mean and standard deviation are themselves the
      appropriate measures for the data in question. The sample distributions I am
      so far seeing don't strongly suggest that. We can see if any more data come
      in (it's a little late, but there is no point adopting a draconic
      interpretation of the previously announced deadline). I still favor the 100%
      sample method, and the variability of the chapter samples so far seems to
      make that reasonable: there is a sort of centerish point in each chapter
      sample, but that centerish point migrates quite a bit between one chapter
      and the next (though the total size of the range stays nearly constant).
      Exactly what happens (to mention only one alternative) when one tries to pin
      down the mean of a Cauchy distribution.

      E Bruce Brooks
      University of Massachusetts at Amherst
    Your message has been successfully submitted and would be delivered to recipients shortly.