Archived posting to the Leica Users Group, 1997/09/02

[Author Prev] [Author Next] [Thread Prev] [Thread Next] [Author Index] [Topic Index] [Home] [Search]

Subject: Re: M6 problem "survey"
From: "shawnl@earthlink.net" <shawnl@earthlink.net>
Date: Wed, 03 Sep 1997 01:40:31 -0400

>Eric,
>
>Are you a statistican?  I am not, but often quite small samples are
>valid.

I am not a statistician either, but in my experience with statistics in 
the sciences, it is a generally accepted principle that smaller samples 
are not reliable when making generalizations about a much larger group.  
It is similar to a person pulling ten marbles out of a bag and assuming 
that since five of the marbles removed are blue, 50 percent of the 
marbles everywhere in the world are blue (when those might, in fact, be 
the only five blue marbles anywhere).  When you examine only a few dozen 
cameras out of tens of thousands produced, you are not eliminating the 
possibility that many LUGers just had the bad luck of getting faulty 
cameras out of a mostly good lot or that there are other factors involved.

>
>But I think the intent was to get a feeling of the experiences of the
>listmembers regarding this. 
>

In that context, I think the survery was a great idea.  But it should be 
left at that.