In article <[EMAIL PROTECTED]>,
Jerry Dallal <[EMAIL PROTECTED]> wrote:
>Find_Housing wrote:
>> "David Heiser" <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>...
....................
>I'm not sure that's your question for a few reasons. Your real question
>seems to be about the actual bacterial concentration level in the bag,
>not that it's 10 or 1000. If it's a liquid and the bacteria don't clump
>(or else see Student's paper on haemacytometers--Bk, 5, 351-360), your
>ability to estimate the concentration will be determined by the
>uncertainty in your measuring instrument, that is, the measuring
>instrument will determine how many samples you need to determine the
>concentration to a particular precision. It would like testing for
>something in your blood. We rarely require a pint because we might miss
>the virus in a particular tube.
About 50 years ago, the question came up about estimating the
concentration of bacteria with a given relative error with a
given confidence. The method being used was to count colonies
on a screen.
In a paper of which I am a coauthor, the simple method was to
count until a given number of particles was observed, instead
of counting a specific amount. This turns out not to be too
difficult; we were told that it is easier than the other.
Now if instead of estimating, it was desired to test, if at all
possible a sequential procedure should be used.
--
This address is for information only. I do not claim that these views
are those of the Statistics Department or of Purdue University.
Herman Rubin, Department of Statistics, Purdue University
[EMAIL PROTECTED] Phone: (765)494-6054 FAX: (765)494-0558
.
.
=================================================================
Instructions for joining and leaving this list, remarks about the
problem of INAPPROPRIATE MESSAGES, and archives are available at:
. http://jse.stat.ncsu.edu/ .
=================================================================
