From: Peter Dalgaard BSA (p.dalgaard@biostat.ku.dk)
Date: Fri 08 Mar 2002 - 23:44:27 EST
Message-id: <x2elivns9g.fsf@blueberry.kubism.ku.dk>
"jimi adams" <imij@columbus.rr.com> writes:
> i am trying to use the
> sample command and have one question about it:
> i am getting the error
>
> Error in sample(length(x), size, replace, prob) :
> insufficient positive probabilities
>
> when i use something like:
> sample (1:4, prob=c(0,0,1,0))[1]
>
> i was expecting that to return a 3 every time
> while this is not exactly what i am using it for, i need the capabilities to
> deal with zeros (as the probability valuees that i will be using wil vary,
> and sometimes will include zeros), and this seems like the zero's are the
> problem...
>
> currently i am assigning zero values in my initial probability vector to a
> miniscule value(1E-4)
>
> is there a more efficient way to deal with this, or another command that
> does a similar thing to only select a single element, where as sample orders
> the entire set according to the prob?
sample (1:4, size=1, prob=c(0,0,1,0))
======
The default is size=4 and subsetting the result doesn't change that.
Notice that this is sampling without replacement, so what is the
algorithm supposed to do when the first element has been sampled?
-- O__ ---- Peter Dalgaard Blegdamsvej 3 c/ /'_ --- Dept. of Biostatistics 2200 Cph. N (*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918 ~~~~~~~~~~ - (p.dalgaard@biostat.ku.dk) FAX: (+45) 35327907 -.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.- r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html Send "info", "help", or "[un]subscribe" (in the "body", not the subject !) To: r-help-request@stat.math.ethz.ch _._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._
This archive was generated by hypermail 2.1.3 : Wed 16 Oct 2002 - 11:56:58 EST