|
Authored by: Chromatix on Saturday, June 23 2012 @ 07:42 AM EDT |
It is a wise man indeed who automatically thinks critically and skeptically when
presented with statistics.[ Reply to This | Parent | # ]
|
|
Authored by: Anonymous on Saturday, June 23 2012 @ 07:59 AM EDT |
I'm reminded of another saying -
Figures don't lie, but liars can figure.[ Reply to This | Parent | # ]
|
|
Authored by: hardmath on Saturday, June 23 2012 @ 08:56 AM EDT |
A notoriously difficult problem in statistical estimation is how to parameterize
the tails of a sample distribution.
If we allowed Oracle the unsupported assumption that the small handful of
patents in suit happened to represent the highest value tail (why?), then an a
posteriori implication is that most of their portfolio must be worthless because
most of the patents Oracle claimed Google infringed were invalid.
---
"Prolog is an efficient programming language because it is a very stupid theorem
prover." -- Richard O'Keefe[ Reply to This | Parent | # ]
|
|
Authored by: FreeChief on Saturday, June 23 2012 @ 12:09 PM EDT |
My brain overheats and closes down whenever I read the word
'statistics'.
I understand the basics of statisics tolerably
well, but so what? I don't understand why it's not contempt of court to even
start down this path.
I think my neighbor has taken something from my yard.
I take him to court and charge him with theft. Rather than present evidence to
show that it was valuable (not a cigarette butt), I present a statistical study
of the average value of goods taken in bank robberies.
Will the court, or
anyone else, care to argue about statistical power and Chi-square fitting of
distributions?
Or will I feel the bump of the bailiffs disdain on the
backside of my pitiful case?
— Programmer in Chief
[ Reply to This | Parent | # ]
|
|
|
|
|