s-news
[Top] [All Lists]

Errors in variables

To: <s-news@lists.biostat.wustl.edu>
Subject: Errors in variables
From: "Jacob van Wyk" <jlvw@rau.ac.za>
Date: Thu, 30 May 2002 12:21:23 +0200
Hi everyone
I was wondering if any member of the group could give me some advice on
a statistical question (I realise it is not directly related to S-Plus,
at least not yet).
From practical considerations I am faced with the following setup:
3 measurements (assumed independent) to measure a random quantity C
(with mean m and sd s, say). The measurement model is:
y1 = C + e1
y2 = C + e2
y3 = C + e3
There are n observations (where each correspond to the three
measurements). The errors e1, e2, e3 have different variances; typically
the variance of e1 is much smaller than the variances of e1 and e2
(which are similar in magnitude). The objective is to find a point - and
interval estimate of var(e1).
Can anybody perhaps aid with any suggestion of how to tackle this
problem?
Thanks!
Jacob


Jacob L van Wyk
Department of Mathematics and Statistics
Rand Afrikaans University
P O Box 524
Auckland Park 2006
South Africa
Tel: +27-11-489-3080
Fax: +27-11-489-2832


<Prev in Thread] Current Thread [Next in Thread>
  • Errors in variables, Jacob van Wyk <=