Here are pages with some info:

http://davidmlane.com/hyperstat/hypothesis_testing_se.html

http://www.psychstat.smsu.edu/introbook/sbk19.htm



> -----Original Message-----
> From: [EMAIL PROTECTED] 
> [mailto:[EMAIL PROTECTED] On Behalf Of Paige Miller
> Sent: 18 December 2003 13:40
> To: [EMAIL PROTECTED]
> Subject: Re: standard error
> 
> 
> Doug wrote:
> > Hi,
> > 
> > I was sitting through a presentation of some research 
> yesterday about 
> > the results of a pilot study where a control group was 
> compared with a 
> > treatment group and I found that I was rather confused 
> about the use 
> > of the term standard error.  The researcher appeared to be saying 
> > something about having too small a standard error was not a good 
> > thing.
> 
> If you compute a statistic (such as a mean), the variability of that 
> statistic is often expressed as the standard error of that statistic.
> 
> > Could someone please explain or link me to a page where I could get 
> > some detailed information about use of the standard error.  I think 
> > that it is a measure of the standard deviation of the sample means, 
> > but this doesn't appear to be the context that was used (from my 
> > understanding).
> 
> The term standard error can apply to statistics other than the mean.
> 
> > When is it good to have a large standard error?  When is it good to 
> > have a small standard error?  Do these answers differ for different 
> > tests and different experimental designs?
> 
> In some situations, a small standard error is not good. In most 
> situations, a small standard error is good.
> 
> In comparing means, a small standard error is a good thing. If it 
> gets really small, it can result in finding almost any two means to 
> be significantly different. Some people think this is a bad thing, 
> but it is not ... the problem is that people don't undesrtand that 
> there is a difference between finding statistically significant 
> differences and practically significant diffences. With very small 
> standard errors, you may find means that are different by 0.01 to be 
> significantly different, when in fact a subject matter expert may 
> not think that differences less than a 1 are of any importance. 
> (When this happens, it may indicate you have too large of a sample 
> size, giving your test far more power than it needs)
> 
> A situation where a very small standard error may not be good is 
> when you are fitting a model of some sort ... a very small standard 
> error MAY indicate overfitting, which is not good ... but a very 
> small standard error MAY ALSO indicate a very good model.
> 
> -- 
> Paige Miller
> Eastman Kodak Company
> paige dot miller at kodak dot com
> http://www.kodak.com
> 
> "It's nothing until I call it!" -- Bill Klem, NL Umpire
> "When you get the choice to sit it out or dance, I hope you dance" 
> -- Lee Ann Womack
> 
> .
> . =================================================================
> Instructions for joining and leaving this list, remarks about 
> the problem of INAPPROPRIATE MESSAGES, and archives are available at:
> .                  http://jse.stat.ncsu.edu/                    .
> =================================================================
> 

.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
.                  http://jse.stat.ncsu.edu/                    .
=================================================================

Reply via email to