On Mar 7, 2011, at 19:12 , Bentley Coffey wrote:
Just to tie up this thread, I wanted to report my solution:
When (n-1)p is an integer, there is a closed form solution:
pbinom(j-1,n,...)
When it is not an integer, its fairly easy to approximate the solution by
interpolating between the
Just to tie up this thread, I wanted to report my solution:
When (n-1)p is an integer, there is a closed form solution:
pbinom(j-1,n,...)
When it is not an integer, its fairly easy to approximate the solution by
interpolating between the closed-form solutions: fitting log(1 - probability
from
Duncan,
I'm not sure how I missed your message. Sorry. What you describe is what I
do when (n-1)p is an integer so that R computes the sample quantile using a
single order statistic. My later posting has that exact binomial expression
in there as a special case. When (n-1)p is not an integer then
I need to calculate the probability that a sample quantile will exceed a
threshold given the size of the iid sample and the parameters describing the
distribution of each observation (normal, in my case). I can compute the
probability with brute force simulation: simulate a size N sample, apply
-project.org wrote on 02/14/2011 09:58:09 AM:
[image removed]
[R] CDF of Sample Quantile
Bentley Coffey
to:
r-help
02/14/2011 01:58 PM
Sent by:
r-help-boun...@r-project.org
I need to calculate the probability that a sample quantile will exceed a
threshold given the size
On 14/02/2011 9:58 AM, Bentley Coffey wrote:
I need to calculate the probability that a sample quantile will exceed a
threshold given the size of the iid sample and the parameters describing the
distribution of each observation (normal, in my case). I can compute the
probability with brute force
still a room when its empty? Does the room,
the thing itself have purpose? Or do we, what's the word... imbue it.
- Jubal Early, Firefly
r-help-boun...@r-project.org wrote on 02/14/2011 09:58:09 AM:
[image removed]
[R] CDF of Sample Quantile
Bentley Coffey
to:
r-help
7 matches
Mail list logo