Statalist The Stata Listserver

[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: RE: Means test (and "robust" variances)

From   "Newson, Roger B" <>
To   <>
Subject   st: RE: Means test (and "robust" variances)
Date   Wed, 14 Feb 2007 18:22:53 -0000

I don't know who or what DAAS 2003 is. However, if you want to estimate
a standard error for the mean of a subpopulation represented by only one
unit in a sample, then, in general, you have to use a non-Huber sampling
variance estimate, and so estimate the population variability of the
subpopulation using the sample variability of other subpopulations. To
do this, you must assume that the variability of the different
subpopulations has a common pattern, such as an equal variance, as
assumed by the equal-variance t-test. I do not know how valid an
assumption this is in your case.

I hope this helps.

Best wishes


Roger Newson
Lecturer in Medical Statistics
Respiratory Epidemiology and Public Health Group
National Heart and Lung Institute
Imperial College London
Royal Brompton campus
Room 33, Emmanuel Kaye Building
1B Manresa Road
London SW3 6LR
Tel: +44 (0)20 7352 8121 ext 3381
Fax: +44 (0)20 7351 8322

Opinions expressed are those of the author, not of the institution.

-----Original Message-----
Sent: 14 February 2007 17:44
Subject: st: Means test

I am working with a complex sample design data(DAAS 2003).Trying to
calculate the subpop mean STATA wont produce Se due to stratum with
single sampling unit.Are there any suggestions on how to overcome this

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2017 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index