RE: Eight people w/ eight controls?

[Jack_Earley@RL.GOV]

I guess it's just my pragmatic side coming through. I have no problem w/

destructive testing only one sample from a lot to verify manufacturing to

specifications, but to apply nonrepresentative sample results to a variant

population seems unreasonable.



Jack Earley

Radiological Engineer





-----Original Message-----

From: Bradshaw, Keith [mailto:Keith.Bradshaw@NNC.CO.UK]

Sent: Thursday, December 20, 2001 4:50 AM

To: radsafe@list.vanderbilt.edu

Subject: Eight people w/ eight controls? 







>The thing that caught my attention most was the size, or lack of, in the

>sample. Eight people w/ eight controls? It's been a long time since my stat

>courses, but I seem to recall needing a minimum of 30 before the data are

>significant.



I think what you recall is you need a minimum of 30 data points to get a

good estimate of the population standard deviation.  But if we believe the

statisticians, it's quite in order to find if two samples (of any n>1 each)

are drawn from the same or different populations at a given level of

confidence.  For approximately normally-distributed results you do this with

the "F-test" coupled with the "t-test".  I'm not saying that this is what

was done in this case, I'm just saying it's possible.  These are in stats

text-books (no doubt there are also more sophisticated tests).



Happy Christmas Radsafers:)



Personal views only



Regards



Keith Bradshaw



Keith Bradshaw

keith.bradshaw@nnc.co.uk

New NNC web site: http://www.nnc.co.uk







****************************************************************************

*********

 NNC Limited

 Booths Hall

 Chelford Road

 Knutsford

 Cheshire

 WA16 8QZ

 

 Country of Registration: United Kingdom

 Registered Number: 1120437

 

 This e-mail and any files transmitted with it are confidential and 

 intended solely for the use of the individual or entity to whom they   

 are addressed. If you have received this e-mail in error please notify 

 the NNC system manager by e-mail at eadm@nnc.co.uk.

****************************************************************************

*********

************************************************************************

You are currently subscribed to the Radsafe mailing list. To unsubscribe,

send an e-mail to Majordomo@list.vanderbilt.edu  Put the text "unsubscribe

radsafe" (no quote marks) in the body of the e-mail, with no subject line.

************************************************************************

You are currently subscribed to the Radsafe mailing list. To unsubscribe,

send an e-mail to Majordomo@list.vanderbilt.edu  Put the text "unsubscribe

radsafe" (no quote marks) in the body of the e-mail, with no subject line.