This mailing list is about R help, not basic statistics help. Your message is
full of what appear to be misconceptions, though it could be just something
basic that affects the whole thing. You should consult with a statistician
locally for most effective communication.
---------------------------------------------------------------------------
Jeff Newmiller The ..... ..... Go Live...
DCN:<jdnewmil@dcn.davis.ca.us> Basics: ##.#. ##.#. Live Go...
Live: OO#.. Dead: OO#.. Playing
Research Engineer (Solar/Batteries O.O#. #.O#. with
/Software/Embedded Controllers) .OO#. .OO#. rocks...1k
---------------------------------------------------------------------------
Sent from my phone. Please excuse my brevity.
Damian Abalo <wardamo.zero@gmail.com> wrote:
Hello, I have a doubt, but it is more statistic than just about R: How
the people deal usually with negative percentile and quartile? In my
concrete case, I want to know the distribution of an error, so the
nearest it is to 0 the better (I think it would be optimun to have the
nearest values to 0 in the lower percentiles). The best result would
be making the percentile of the absolute value (without sign), but the
sing is also important, and I need to keep it.
This results in the big negative values to be in the lower
percentiles, which are usually understanded as the best cases, since
we are working with an error. My question is, what is the usual thing
done in this cases? keep the sign, and read the lower percentiles as
bad cases also (being the optimal ones the center ones) or try to
somehow get the signless distribution keeping the signs somehow? And
if this is the case, how can this be done?
Thanks for your time, Best regards
_____________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
[[alternative HTML version deleted]]