R help - Jan 2011 - confidence interval

Hi,
I have a circular shaped set of point on the plane (X,Y) centered in
zero. The distribution is more dense close to zero and less dense far
from zero.

I need to find the radius of a circle centered in zero that contains
65% of the points in the sample. Is there any R directive that can do
this?

I wanna start with 2D set of points, but the real case scenario is
with a 5D set of points.

Thanks,

Francesco

On Jan 21, 2011, at 11:33 AM, Francesco Petrogalli wrote:
> Hi,
> I have a circular shaped set of point on the plane (X,Y) centered in
> zero. The distribution is more dense close to zero and less dense far
> from zero.
>
> I need to find the radius of a circle centered in zero that contains
> 65% of the points in the sample. Is there any R directive that can do
> this?
>
> I wanna start with 2D set of points, but the real case scenario is
> with a 5D set of points.
Something along the lines of

dxy= with(dfm, sqrt(x^2 +y^2))
quantile(dxy, probs=0.65)

The generalization to 5 dimensions appears trivial. Even the  
generalization to finding the radius around an arbitrary point seems  
trivial assuming an L2 norm.

-- 
David Winsemius, MD
West Hartford, CT

Hi,
I am trying to determine how many points fall ouside the confidence interval
range.

This is the code I have so far but it does not work. Any help would be
appreciated.

Count <- vector ()
for (i in 1: nrow (dataname)){
if (dataname[i] <l.ci.post[1]//
dataname[i] >u.ci.post[i]){
count[i] -> 1
}else
{count[i] -> 0}
}



symbol
// = or - not sure if this is the right symbol though
-- 
View this message in context:
http://r.789695.n4.nabble.com/Confidence-interval-tp3304258p3304258.html
Sent from the R help mailing list archive at Nabble.com.

Hi,

The logical operators are actually vectorized, so I do not think you
need a loop.  Does this do what you want?

## Some data
set.seed(10)
dat <- matrix(rnorm(500, sd = 3), nrow = 80)

## Hypothetical confidence interval
ci <- c(-5, 5)

## Find the number of points outside interval
sum(dat < ci[1] | dat > ci[2], na.rm = TRUE)

Cheers,

Josh

On Sun, Feb 13, 2011 at 4:26 PM, Syd88 <jhea2850 at uni.sydney.edu.au>
wrote:
>
> Hi,
> I am trying to determine how many points fall ouside the confidence
interval
> range.
>
> This is the code I have so far but it does not work. Any help would be
> appreciated.
>
> Count <- vector ()
> for (i in 1: nrow (dataname)){
> if (dataname[i] <l.ci.post[1]//
> dataname[i] >u.ci.post[i]){
> count[i] -> 1
> }else
> {count[i] -> 0}
> }
>
>
>
> symbol
> // = or - not sure if this is the right symbol though
> --
> View this message in context:
http://r.789695.n4.nabble.com/Confidence-interval-tp3304258p3304258.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> R-help at 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.
>


-- 
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/