[R] Non : Confidence intervals for p**2 ??

[(Ted Harding)]

On 05-Mar-07 Öhagen Patrik wrote:
> 
> Dear List,
> 
> I was asked to calculate a confidence interval for p*p. Is there any
> standard techniques for calculating such an interval? Delta Method?
> 
> Thank you in advance!
> 
> Cheers, Patrik

If "p" is meant to denote a probability between 0 and 1, then

  pL^2 < p^2 < pU^2

is exactly equivalent to

  pL < p < pU

where pL and pU are the upper and lower limits for p. Indeed, this
will be so if p is any quantity which is necessarily non-negative.

Hence, if this is your situation, simply square the confidence
limits for p.

If, however, this is not your situation, then please explain
what "p" represents.

Best wishes,
Ted.

--------------------------------------------------------------------
E-Mail: (Ted Harding) <ted.harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861
Date: 05-Mar-07                                       Time: 10:05:50
------------------------------ XFMail ------------------------------