It's called a 2-sided 95% Prediction Interval. Like the Prediction Interval in a regression.
In general, you can work out a (2-sided) 95% prediction interval for a variable X with any distribution by excluding the values x for which
P(X <= x) <= 0.025
P(X >= x) <= 0.025
If X is continuous, the limits of the interval are the values x1 and x2 such
that
P(X <= x1) = 0.025
P(X >= x2) = 0.025
If X is normal, x1 = mean - 2sd, x2 = mean + 2sd (approximately).
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Rodney Carr
School of Management Information Systems
Deakin University
PO Box 423
Warrnambool VIC 3280
Australia
email: [log in to unmask] phone: + 61 3 5563 3458
mobile: 0417 307 692 fax: + 61 3 5563 3320
www: http://www.man.deakin.edu.au/rodneyc
-----Original Message-----
From: tra [SMTP:[log in to unmask]]
Sent: Wednesday, September 13, 2000 10:00 PM
To: [log in to unmask]
Subject: QUERY: Confidence interval for individual measurements.
A 95% confidence interval for a population mean is well known and often
calculated as approximately mean +/- 2*(standard-error-of-the-mean).
My question is, what is the most common and easily understood term for
an interval with end-points mean +/- 2*SD which will contain 95% of the
individual values of a population. The ends of the interval are
estimates of the 2.5 and 97.5 percentiles of the distribution.
Thanks
Tim
--
T R Auton PhD MSc C.Math
Head of Biomedical Statistics
Protherics Molecular Design Ltd
Beechfield House
Lyme Green Business Park
Macclesfield
Cheshire SK11 0JL
UK
email: [log in to unmask]
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
|