Step 1: Read the R-FAQ 7.31:
Step 2: Ask yourself whether it is likely that such a small value can
be sensibly distinguished from zero using a program that stores values
in double precision.
Step 3: Consider alternate methods, perhaps logarithms or programs
that are equipped to deal with arbitrary precision. There have been
threads on such strategies. I got on-topic results with an r-search
on : "very small" log probabilit*
--
David Winsemius
On Feb 12, 2009, at 2:09 PM, Tim Smith wrote:
Hi all,
I was working with some probabilities and wanted to store some small
values. For example:
x = 2e-250
x
[1] 2e-250
y = 2e-300
y
[1] 2e-300
z = 2e-350
z
[1] 0
Is there any way to store a small value (e.g. 2e-350) in R?
thanks!
[[alternative HTML version deleted]]
______________________________________________
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.
______________________________________________
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.
