On 21/10/14 03:41, Ranjan Maitra wrote:
On Mon, 20 Oct 2014 00:16:42 +0100 Patrick O'Callaghan <pocallaghan@xxxxxxxxx> wrote:
On Mon, 2014-10-20 at 08:31 +1300, Rolf Turner wrote:
On 20/10/14 01:28, Patrick O'Callaghan wrote:
On Sat, 2014-10-18 at 01:10 +0000, Bill Oliver wrote:
Here's the problem. Let's say you have a set of data and you want to
characterize it in order to use it as the basis of a model. In order
to do that, you really need to know the underlying PDF.
I assume you mean Probability Distribution Function, not Portable
Document Format. That might not be clear to everyone, particularly on a
list such as this one.
Probability *density* function, actually. :-)
It can be either Distribution or Density. Also a few other things (see
Wikipedia).
Hi,
I believe that Rolf and I (and Bill O) were referencing PDFs from a
probabilistic/statistical perspective. I don't quite know how
Wikipedia places as a quality reference for expertise in everything
(I use it more to find references for further reading), but in
probability, a pdf expands to a probability density function. There
is a no such thing as a probability distribution function because as
noted, the term itself is ambiguous and imprecise. Precise statements
(even when quantifying imprecision) are always preferred in
scientific literature. Of course, some undergraduate texts also must
share the blame: nowadays I have noticed that they pretty much define
anything any way. (Example: many authors incorrectly call the
probability mass function as a probability density function, perhaps
just to be different -- but which is why you have inattentive
students integrating the binomial pmf in tests and getting lost...).
That's the problem with specialist terminology where the context
isn't completely clear, e.g. we all know what ATM is when talking
about a banking network, right? (Asynchronous Transfer Mode). Or
DOS when talking about computers (Denial Of Service). I could go
on.
Of course, there will be confusion between Probability Density
Function and Portable Document Format, because they are from
different areas and hence the smiley:-) The same does not hold for
the example referenced above.
Sorry to be a stickler on this:-)
*Extremely* well put! Thank you Ranjan!
cheers,
Rolf
--
Rolf Turner
Technical Editor ANZJS
--
users mailing list
users@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe or change subscription options:
https://admin.fedoraproject.org/mailman/listinfo/users
Fedora Code of Conduct: http://fedoraproject.org/code-of-conduct
Guidelines: http://fedoraproject.org/wiki/Mailing_list_guidelines
Have a question? Ask away: http://ask.fedoraproject.org
