Re: Fw: min / max and empty intervals - Entire and Missing Data
On Jun 9 2011, Ian McIntosh wrote:
So here are my questions: Can we define a decoration for "missing data" or
"unknown", and decoration operations which when encountering that produce
"some data is missing" or "some data is unknown"? Is it better to define
specific operations to be used in such cases (eg, max_known_value)? Can
either or both of those be done in a consistent way? Can they be done
without damaging other things? Would that increase (or decrease?) the
usefulness of the standard?
The answers according to all existing practice are "perhaps", "yes", "yes",
"yes" and "probably increase". To see what that practice is, look at any
good statistical package. I believe that missing values in the modern
sense were invented and first used by Rothamsted Experimental Station
(like so many things in statistics) in some of the predecessors of
Genstat. Genstat is a good package to look at for this, incidentally.
As I posted earlier, missing values are very like Entire, except when
used in the reductions and interpolations that are designed to handle
them. However, true Entire/NaN/error is a higher priority value and
addition over an array is not necessarily a reduction in this sense.
It is a cardinal error to treat error values as missing, except with
GREAT care and lots of reservations, in interpolations.
Regards,
Nick Maclaren.