[PREV - PRECISELY_ACCURATE]    [TOP]

SCATTER_THE_PAGES

                                             December 30, 2023


My original intention in reading the book

  "Noise" (2021) by Kahneman, Sibony and Sunstein

was to dig it and study it closely.


But consider this passage (p.75-6):


   "We use the term *pattern noise* for the
    variability we just identified because that
    variability reflects a complex pattern in
    the attitudes of judges to particular cases.
    One judge, for instance, may be harsher than
    average in general but relatively more
    lenient toward white collar criminals."          In earlier material
                                                     in this book, they
                                                     use the more common
                                                     term of "bias".

                                                     If there's some reason
                                                     "pattern noise" differs
                                                     from "bias" (perhaps the
                                                     latter is a subset?) it's
                                                     not made clear in this
                                                     part of the text, which
                                                     does not refer to bias
                                                     anywhere.

And further:

   "(We use the term *pattern noise* in the
   interests of readability.  The proper
   statistical term for pattern noise is
   *judge x case interaction*-- pronounced
   'judge by case.'  We apologize to people
   with statistical training by imposing the
   burden of translation on them.)"

                                                      MEDIUM_SPEED

I might propose some additional text
to insert at this point:


   We apologize to the reader for discussing standard
   statistical subjects, but obscuring the connections to
   it with our own invented jargon.

   We apologize to the reader from switching jargon
   between chapters, and introducing a new piece of
   terminology for something we referred to by a
   more common name in a previous chapter.

   We ask the readers indulgence in our attempts
   at portraying well-known understandings as a fresh
   insights on our part, and hope you will support
   our attempts at convincing potential employers
   that we are geniuses well-suited to work as
   consultants.










--------
[NEXT - SCATTERING_THE_NOISE_FILTER]